github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11434] crash when running gemma3 model and ask it to calculate the time between two dates. #54061

New Issue
Closed
opened 2026-04-29 05:10:08 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-29 05:10:08 -05:00
Owner
Copy Link

Originally created by @abcbarryn on GitHub (Jul 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11434

What is the issue?

I asked the model to calculate the length of time between July 15th, 2025 and July 25th, 2025 and it start shuttering and then crashed.

Relevant log output

Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.026-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.029-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41521"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1

OS

SuSE Linux

GPU

None

CPU

Two CPUs with 14 cores each.

Ollama version

ollama version is 0.9.6

Originally created by @abcbarryn on GitHub (Jul 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11434 ### What is the issue? I asked the model to calculate the length of time between July 15th, 2025 and July 25th, 2025 and it start shuttering and then crashed. ### Relevant log output ```shell Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.026-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.029-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41521" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 ``` ### OS SuSE Linux ### GPU None ### CPU Two CPUs with 14 cores each. ### Ollama version ollama version is 0.9.6
GiteaMirror added the bug label 2026-04-29 05:10:08 -05:00
GiteaMirror commented 2026-04-29 05:10:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 15, 2025):

The log doesn't show a crash.

<!-- gh-comment-id:3075656059 --> @rick-github commented on GitHub (Jul 15, 2025): The log doesn't show a crash.
GiteaMirror commented 2026-04-29 05:10:12 -05:00
Author
Owner
Copy Link

@abcbarryn commented on GitHub (Jul 15, 2025):

Maybe the model crashed? Something crashed. The terminal was stuck in a shuttering output loop until I pressed CTRL-C.

<!-- gh-comment-id:3075898228 --> @abcbarryn commented on GitHub (Jul 15, 2025): Maybe the model crashed? Something crashed. The terminal was stuck in a shuttering output loop until I pressed CTRL-C.
GiteaMirror commented 2026-04-29 05:10:13 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 15, 2025):

Perhaps if you add more than 4 lines of log.

<!-- gh-comment-id:3075933811 --> @rick-github commented on GitHub (Jul 15, 2025): Perhaps if you add more than 4 lines of log.
GiteaMirror commented 2026-04-29 05:10:14 -05:00
Author
Owner
Copy Link

@abcbarryn commented on GitHub (Jul 15, 2025):

Jul 15 01:06:05 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:05 | 200 |       43.89µs |       127.0.0.1 | HEAD     "/"
Jul 15 01:06:05 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:05 | 200 |      34.607µs |       127.0.0.1 | GET      "/api/ps"
Jul 15 01:06:15 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:15 | 200 |      34.303µs |       127.0.0.1 | HEAD     "/"
Jul 15 01:06:15 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:15 | 200 |  199.449466ms |       127.0.0.1 | POST     "/api/show"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.135-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.7 GiB" free_swap="29.7 GiB"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.138-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.236-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 33357"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.237-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.237-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.237-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.253-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.254-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:33357"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.344-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 01:06:16 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.351-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.489-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.666-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.962-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 01:06:17 amobile ollama[17467]: time=2025-07-15T01:06:17.762-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.53 seconds"
Jul 15 01:06:17 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:17 | 200 |   1.92506674s |       127.0.0.1 | POST     "/api/generate"
Jul 15 01:09:41 amobile ollama[17467]: [GIN] 2025/07/15 - 01:09:41 | 200 |         2m42s |       127.0.0.1 | POST     "/api/chat"
Jul 15 01:12:48 amobile ollama[17467]: [GIN] 2025/07/15 - 01:12:48 | 200 |          2m0s |       127.0.0.1 | POST     "/api/chat"
Jul 15 01:19:34 amobile ollama[17467]: [GIN] 2025/07/15 - 01:19:34 | 200 |         2m42s |       127.0.0.1 | POST     "/api/chat"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.026-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.029-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41521"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.149-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.168-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.168-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:41521"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.273-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 01:24:42 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.280-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.285-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.286-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.286-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.286-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.401-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.570-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.747-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 01:24:43 amobile ollama[17467]: time=2025-07-15T01:24:43.911-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.76 seconds"
Jul 15 01:27:35 amobile ollama[17467]: [GIN] 2025/07/15 - 01:27:35 | 200 |         2m53s |       127.0.0.1 | POST     "/api/chat"
Jul 15 01:33:05 amobile ollama[17467]: [GIN] 2025/07/15 - 01:33:05 | 200 |  37.98540726s |       127.0.0.1 | POST     "/api/chat"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.619-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.621-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.716-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41437"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.716-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.716-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.717-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.734-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.736-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:41437"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.827-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 01:40:16 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.834-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.968-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 01:40:17 amobile ollama[17467]: time=2025-07-15T01:40:17.113-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 01:40:17 amobile ollama[17467]: time=2025-07-15T01:40:17.288-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 01:40:18 amobile ollama[17467]: time=2025-07-15T01:40:18.226-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.51 seconds"
Jul 15 01:41:38 amobile ollama[17467]: [GIN] 2025/07/15 - 01:41:38 | 200 |         1m22s |       127.0.0.1 | POST     "/api/chat"
Jul 15 01:44:40 amobile ollama[17467]: [GIN] 2025/07/15 - 01:44:40 | 200 |          1m3s |       127.0.0.1 | POST     "/api/chat"
Jul 15 01:49:32 amobile ollama[17467]: [GIN] 2025/07/15 - 01:49:32 | 200 |   26.3552658s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:00:49 amobile ollama[17467]: [GIN] 2025/07/15 - 02:00:49 | 200 |      39.415µs |       127.0.0.1 | HEAD     "/"
Jul 15 02:00:49 amobile ollama[17467]: [GIN] 2025/07/15 - 02:00:49 | 200 |  182.084631ms |       127.0.0.1 | POST     "/api/show"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.063-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.065-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.166-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 45897"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.167-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.167-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.167-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.185-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.185-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:45897"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.274-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 02:00:50 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.281-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.286-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.287-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.287-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.287-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.419-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.575-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.848-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 02:00:51 amobile ollama[17467]: time=2025-07-15T02:00:51.684-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.52 seconds"
Jul 15 02:00:51 amobile ollama[17467]: [GIN] 2025/07/15 - 02:00:51 | 200 |  1.910645146s |       127.0.0.1 | POST     "/api/generate"
Jul 15 02:04:07 amobile ollama[17467]: [GIN] 2025/07/15 - 02:04:07 | 200 |         2m49s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:06:47 amobile ollama[17467]: [GIN] 2025/07/15 - 02:06:47 | 200 |         2m12s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:10:37 amobile ollama[17467]: [GIN] 2025/07/15 - 02:10:37 | 200 |         2m24s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:13:36 amobile ollama[17467]: [GIN] 2025/07/15 - 02:13:36 | 200 |         1m45s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:18:37 amobile ollama[17467]: [GIN] 2025/07/15 - 02:18:37 | 200 |         1m29s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:20:22 amobile ollama[17467]: [GIN] 2025/07/15 - 02:20:22 | 200 | 24.101449501s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:22:28 amobile ollama[17467]: [GIN] 2025/07/15 - 02:22:28 | 200 |         1m16s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:24:37 amobile ollama[17467]: [GIN] 2025/07/15 - 02:24:37 | 200 |         1m15s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:26:57 amobile ollama[17467]: [GIN] 2025/07/15 - 02:26:57 | 200 |         1m14s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:31:07 amobile ollama[17467]: [GIN] 2025/07/15 - 02:31:07 | 200 |         2m13s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:32:33 amobile ollama[17467]: [GIN] 2025/07/15 - 02:32:33 | 200 | 11.564672162s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:36:32 amobile ollama[17467]: [GIN] 2025/07/15 - 02:36:32 | 200 |         2m21s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:41:53 amobile ollama[17467]: [GIN] 2025/07/15 - 02:41:53 | 200 | 46.782257017s |       127.0.0.1 | POST     "/api/chat"
Jul 15 02:43:59 amobile ollama[17467]: [GIN] 2025/07/15 - 02:43:59 | 200 |          1m3s |       127.0.0.1 | POST     "/api/chat"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.463-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.0 GiB"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.465-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.561-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41967"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.562-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.562-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.562-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.577-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.577-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:41967"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.664-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 10:58:17 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.671-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.814-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.966-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 10:58:18 amobile ollama[17467]: time=2025-07-15T10:58:18.140-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 10:58:19 amobile ollama[17467]: time=2025-07-15T10:58:19.581-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds"
Jul 15 10:58:23 amobile ollama[17467]: [GIN] 2025/07/15 - 10:58:23 | 200 |  6.619394623s |       127.0.0.1 | POST     "/api/chat"
Jul 15 10:58:51 amobile ollama[17467]: [GIN] 2025/07/15 - 10:58:51 | 200 |  2.678771024s |       127.0.0.1 | POST     "/api/chat"
Jul 15 10:59:28 amobile ollama[17467]: [GIN] 2025/07/15 - 10:59:28 | 200 | 16.793880245s |       127.0.0.1 | POST     "/api/chat"
Jul 15 11:01:09 amobile ollama[17467]: [GIN] 2025/07/15 - 11:01:09 | 200 |  5.583076216s |       127.0.0.1 | POST     "/api/chat"
Jul 15 12:24:46 amobile ollama[17467]: [GIN] 2025/07/15 - 12:24:46 | 200 |      56.614µs |       127.0.0.1 | HEAD     "/"
Jul 15 12:24:46 amobile ollama[17467]: [GIN] 2025/07/15 - 12:24:46 | 200 |   187.47452ms |       127.0.0.1 | POST     "/api/show"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.225-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.0 GiB"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.227-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 38447"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.340-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.341-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:38447"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.430-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 12:24:47 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.437-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.576-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.743-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 12:24:48 amobile ollama[17467]: time=2025-07-15T12:24:48.011-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 12:24:49 amobile ollama[17467]: time=2025-07-15T12:24:49.594-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.27 seconds"
Jul 15 12:24:49 amobile ollama[17467]: [GIN] 2025/07/15 - 12:24:49 | 200 |  2.646873422s |       127.0.0.1 | POST     "/api/generate"
Jul 15 12:28:09 amobile ollama[17467]: [GIN] 2025/07/15 - 12:28:09 | 200 |         2m41s |       127.0.0.1 | POST     "/api/chat"
Jul 15 12:30:20 amobile ollama[17467]: [GIN] 2025/07/15 - 12:30:20 | 200 | 46.245741541s |       127.0.0.1 | POST     "/api/chat"
Jul 15 12:31:18 amobile ollama[17467]: [GIN] 2025/07/15 - 12:31:18 | 200 | 40.434622179s |       127.0.0.1 | POST     "/api/chat"
Jul 15 12:32:04 amobile ollama[17467]: [GIN] 2025/07/15 - 12:32:04 | 200 | 11.571502803s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.853-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.3 GiB" free_swap="30.1 GiB"
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.855-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 43873"
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.975-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.976-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:43873"
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.077-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 14:06:00 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.084-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.207-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.381-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.559-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 14:06:01 amobile ollama[17467]: time=2025-07-15T14:06:01.977-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds"
Jul 15 14:06:14 amobile ollama[17467]: [GIN] 2025/07/15 - 14:06:14 | 200 | 15.243695865s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:08:49 amobile ollama[17467]: [GIN] 2025/07/15 - 14:08:49 | 200 |   7.81688474s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:10:32 amobile ollama[17467]: [GIN] 2025/07/15 - 14:10:32 | 200 |   5.57302473s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:11:52 amobile ollama[17467]: [GIN] 2025/07/15 - 14:11:52 | 200 |  4.563861397s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:12:21 amobile ollama[17467]: [GIN] 2025/07/15 - 14:12:21 | 200 |  7.445482222s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:13:40 amobile ollama[17467]: [GIN] 2025/07/15 - 14:13:40 | 200 |  8.141572187s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:15:38 amobile ollama[17467]: [GIN] 2025/07/15 - 14:15:38 | 200 | 11.704692526s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:17:23 amobile ollama[17467]: [GIN] 2025/07/15 - 14:17:23 | 200 |  8.167364087s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:19:24 amobile ollama[17467]: [GIN] 2025/07/15 - 14:19:24 | 200 |  8.725596273s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:20:54 amobile ollama[17467]: [GIN] 2025/07/15 - 14:20:54 | 200 |  7.287166608s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:23:09 amobile ollama[17467]: [GIN] 2025/07/15 - 14:23:09 | 200 |  7.923928608s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:28:00 amobile ollama[17467]: [GIN] 2025/07/15 - 14:28:00 | 200 |  9.638210214s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:30:20 amobile ollama[17467]: [GIN] 2025/07/15 - 14:30:20 | 200 | 11.398374606s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:32:11 amobile ollama[17467]: [GIN] 2025/07/15 - 14:32:11 | 200 |  6.043563297s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:35:04 amobile ollama[17467]: [GIN] 2025/07/15 - 14:35:04 | 200 | 10.856669259s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:38:09 amobile ollama[17467]: [GIN] 2025/07/15 - 14:38:09 | 200 |  10.15686096s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:39:15 amobile ollama[17467]: [GIN] 2025/07/15 - 14:39:15 | 200 |  6.940100831s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:41:27 amobile ollama[17467]: [GIN] 2025/07/15 - 14:41:27 | 200 | 12.226914926s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:44:28 amobile ollama[17467]: [GIN] 2025/07/15 - 14:44:28 | 200 | 23.563901162s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:48:26 amobile ollama[17467]: [GIN] 2025/07/15 - 14:48:26 | 200 | 33.467552018s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:50:38 amobile ollama[17467]: [GIN] 2025/07/15 - 14:50:38 | 200 | 32.005724467s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:52:51 amobile ollama[17467]: [GIN] 2025/07/15 - 14:52:51 | 200 | 34.606237099s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:55:03 amobile ollama[17467]: [GIN] 2025/07/15 - 14:55:03 | 200 | 39.147461074s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:57:11 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:11 | 200 | 37.597258006s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:57:45 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:45 | 200 |      60.643µs |       127.0.0.1 | HEAD     "/"
Jul 15 14:57:45 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:45 | 200 |      75.829µs |       127.0.0.1 | GET      "/api/ps"
Jul 15 14:57:49 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:49 | 200 |  5.326923899s |       127.0.0.1 | POST     "/api/chat"
Jul 15 14:58:40 amobile ollama[17467]: [GIN] 2025/07/15 - 14:58:40 | 200 |      39.146µs |       127.0.0.1 | HEAD     "/"
Jul 15 14:58:40 amobile ollama[17467]: [GIN] 2025/07/15 - 14:58:40 | 200 |       37.34µs |       127.0.0.1 | GET      "/api/ps"
Jul 15 15:31:24 amobile ollama[17467]: [GIN] 2025/07/15 - 15:31:24 | 200 |      39.551µs |       127.0.0.1 | HEAD     "/"
Jul 15 15:31:24 amobile ollama[17467]: [GIN] 2025/07/15 - 15:31:24 | 200 |  193.354766ms |       127.0.0.1 | POST     "/api/show"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.125-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.127-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 35539"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.237-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.237-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:35539"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.331-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 15:31:25 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.337-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.475-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.638-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.913-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 15:31:27 amobile ollama[17467]: time=2025-07-15T15:31:27.248-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds"
Jul 15 15:31:27 amobile ollama[17467]: [GIN] 2025/07/15 - 15:31:27 | 200 |  2.458372036s |       127.0.0.1 | POST     "/api/generate"
Jul 15 15:32:06 amobile ollama[17467]: [GIN] 2025/07/15 - 15:32:06 | 200 | 12.149772723s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:32:50 amobile ollama[17467]: [GIN] 2025/07/15 - 15:32:50 | 200 | 19.018623689s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:33:40 amobile ollama[17467]: [GIN] 2025/07/15 - 15:33:40 | 200 |  19.08334206s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:34:59 amobile ollama[17467]: [GIN] 2025/07/15 - 15:34:59 | 200 | 26.413488556s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:37:22 amobile ollama[17467]: [GIN] 2025/07/15 - 15:37:22 | 200 | 27.871657486s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:38:35 amobile ollama[17467]: [GIN] 2025/07/15 - 15:38:35 | 200 | 27.072325445s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:40:25 amobile ollama[17467]: [GIN] 2025/07/15 - 15:40:25 | 200 | 38.748835117s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:42:57 amobile ollama[17467]: [GIN] 2025/07/15 - 15:42:57 | 200 |  3.887759995s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:47:15 amobile ollama[17467]: [GIN] 2025/07/15 - 15:47:15 | 200 | 32.823251665s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:47:48 amobile ollama[17467]: [GIN] 2025/07/15 - 15:47:48 | 200 |  8.797014247s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:48:16 amobile ollama[17467]: [GIN] 2025/07/15 - 15:48:16 | 200 | 23.792104523s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:48:38 amobile ollama[17467]: [GIN] 2025/07/15 - 15:48:38 | 200 |   9.21259348s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:49:31 amobile ollama[17467]: [GIN] 2025/07/15 - 15:49:31 | 200 | 21.710448987s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:49:35 amobile ollama[17467]: [GIN] 2025/07/15 - 15:49:35 | 200 | 32.825344864s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:49:40 amobile ollama[17467]: [GIN] 2025/07/15 - 15:49:40 | 200 |  7.626245474s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:50:47 amobile ollama[17467]: [GIN] 2025/07/15 - 15:50:47 | 200 |  6.319395124s |       127.0.0.1 | POST     "/api/chat"
Jul 15 15:50:55 amobile ollama[17467]: [GIN] 2025/07/15 - 15:50:55 | 200 | 16.482319877s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.011-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.1 GiB" free_swap="30.1 GiB"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.013-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.108-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 40683"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.108-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.109-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.109-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.136-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.136-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:40683"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.233-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 16:00:37 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.240-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.361-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.537-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.714-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:00:39 amobile ollama[17467]: time=2025-07-15T16:00:39.125-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds"
Jul 15 16:00:50 amobile ollama[17467]: [GIN] 2025/07/15 - 16:00:50 | 200 | 13.453382374s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:01:37 amobile ollama[17467]: [GIN] 2025/07/15 - 16:01:37 | 200 |  7.010397526s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:02:47 amobile ollama[17467]: [GIN] 2025/07/15 - 16:02:47 | 200 |  9.218088928s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:03:40 amobile ollama[17467]: [GIN] 2025/07/15 - 16:03:40 | 200 |  8.419104993s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:06:18 amobile ollama[17467]: [GIN] 2025/07/15 - 16:06:18 | 200 | 44.640608373s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:06:50 amobile ollama[17467]: [GIN] 2025/07/15 - 16:06:50 | 200 |  17.14751161s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:07:39 amobile ollama[17467]: [GIN] 2025/07/15 - 16:07:39 | 200 | 38.689371786s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:08:12 amobile ollama[17467]: [GIN] 2025/07/15 - 16:08:12 | 200 | 32.899070555s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:08:34 amobile ollama[17467]: time=2025-07-15T16:08:34.345-04:00 level=WARN source=runner.go:157 msg="truncating input prompt" limit=4096 prompt=19010 keep=4 new=4096
Jul 15 16:09:46 amobile ollama[17467]: [GIN] 2025/07/15 - 16:09:46 | 200 | 25.107300894s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:12:18 amobile ollama[17467]: [GIN] 2025/07/15 - 16:12:18 | 200 |         3m43s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:12:19 amobile ollama[17467]: [GIN] 2025/07/15 - 16:12:19 | 200 |         1m36s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:15:05 amobile ollama[17467]: [GIN] 2025/07/15 - 16:15:05 | 200 |         1m53s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:15:38 amobile ollama[17467]: [GIN] 2025/07/15 - 16:15:38 | 200 |         1m14s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:15:48 amobile ollama[17467]: [GIN] 2025/07/15 - 16:15:48 | 200 | 33.070491476s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:17:31 amobile ollama[17467]: [GIN] 2025/07/15 - 16:17:31 | 200 |          1m0s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:21:06 amobile ollama[17467]: [GIN] 2025/07/15 - 16:21:06 | 200 | 34.303595005s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:21:32 amobile ollama[17467]: panic: failed to decode batch: could not find a kv cache slot (cache: 2560 batch: 512)
Jul 15 16:21:32 amobile ollama[17467]: goroutine 8 [running]:
Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002b6900, {0x55867a095700, 0xc0000008c0})
Jul 15 16:21:32 amobile ollama[17467]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x65
Jul 15 16:21:32 amobile ollama[17467]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
Jul 15 16:21:32 amobile ollama[17467]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74
Jul 15 16:21:32 amobile ollama[17467]: time=2025-07-15T16:21:32.337-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:40683/completion\": EOF"
Jul 15 16:21:32 amobile ollama[17467]: [GIN] 2025/07/15 - 16:21:32 | 500 | 11.994152362s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.458-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.461-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.562-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 45949"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.562-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.562-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.563-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.581-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.582-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:45949"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.678-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 16:22:39 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.684-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.814-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.973-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:22:40 amobile ollama[17467]: time=2025-07-15T16:22:40.238-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:22:41 amobile ollama[17467]: time=2025-07-15T16:22:41.844-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.28 seconds"
Jul 15 16:23:21 amobile ollama[17467]: [GIN] 2025/07/15 - 16:23:21 | 200 | 42.358125818s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:35:49 amobile ollama[17467]: time=2025-07-15T16:35:49.962-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB"
Jul 15 16:35:49 amobile ollama[17467]: time=2025-07-15T16:35:49.964-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.062-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 36385"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.062-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.063-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.063-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.080-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.081-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:36385"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.178-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 16:35:50 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.186-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.314-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.481-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.656-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:35:52 amobile ollama[17467]: time=2025-07-15T16:35:52.094-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.03 seconds"
Jul 15 16:36:34 amobile ollama[17467]: [GIN] 2025/07/15 - 16:36:34 | 200 | 44.698539465s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:37:39 amobile ollama[17467]: [GIN] 2025/07/15 - 16:37:39 | 200 | 15.367562581s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:39:19 amobile ollama[17467]: [GIN] 2025/07/15 - 16:39:19 | 200 | 58.985695818s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:39:26 amobile ollama[17467]: [GIN] 2025/07/15 - 16:39:26 | 200 |          1m4s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:40:27 amobile ollama[17467]: [GIN] 2025/07/15 - 16:40:27 | 200 | 32.498111154s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:41:19 amobile ollama[17467]: [GIN] 2025/07/15 - 16:41:19 | 200 | 25.790679315s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:42:42 amobile ollama[17467]: [GIN] 2025/07/15 - 16:42:42 | 200 | 29.962983809s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:44:26 amobile ollama[17467]: [GIN] 2025/07/15 - 16:44:26 | 200 | 20.049622997s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:45:03 amobile ollama[17467]: [GIN] 2025/07/15 - 16:45:03 | 200 | 11.432715593s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:45:30 amobile ollama[17467]: [GIN] 2025/07/15 - 16:45:30 | 200 |  15.81967878s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:47:41 amobile ollama[17467]: [GIN] 2025/07/15 - 16:47:41 | 200 |         1m15s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:49:29 amobile ollama[17467]: [GIN] 2025/07/15 - 16:49:29 | 200 |          3m9s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:51:05 amobile ollama[17467]: [GIN] 2025/07/15 - 16:51:05 | 200 | 14.459985878s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:52:31 amobile ollama[17467]: panic: failed to decode batch: could not find a kv cache slot (cache: 2560 batch: 512)
Jul 15 16:52:31 amobile ollama[17467]: goroutine 14 [running]:
Jul 15 16:52:31 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00065e900, {0x555e3641c700, 0xc0001308c0})
Jul 15 16:52:31 amobile ollama[17467]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x65
Jul 15 16:52:31 amobile ollama[17467]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
Jul 15 16:52:31 amobile ollama[17467]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74
Jul 15 16:52:31 amobile ollama[17467]: time=2025-07-15T16:52:31.866-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:36385/completion\": EOF"
Jul 15 16:52:31 amobile ollama[17467]: [GIN] 2025/07/15 - 16:52:31 | 200 | 13.142628839s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.611-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.613-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 39263"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.739-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.740-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:39263"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.836-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 16:53:23 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.842-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.976-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 16:53:24 amobile ollama[17467]: time=2025-07-15T16:53:24.139-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:53:24 amobile ollama[17467]: time=2025-07-15T16:53:24.409-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 16:53:26 amobile ollama[17467]: time=2025-07-15T16:53:26.009-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.28 seconds"
Jul 15 16:54:38 amobile ollama[17467]: [GIN] 2025/07/15 - 16:54:38 | 200 |         1m15s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:56:20 amobile ollama[17467]: [GIN] 2025/07/15 - 16:56:20 | 200 |          1m9s |       127.0.0.1 | POST     "/api/chat"
Jul 15 16:59:05 amobile ollama[17467]: [GIN] 2025/07/15 - 16:59:05 | 200 |         1m34s |       127.0.0.1 | POST     "/api/chat"
Jul 15 17:00:40 amobile ollama[17467]: [GIN] 2025/07/15 - 17:00:40 | 200 |         1m33s |       127.0.0.1 | POST     "/api/chat"
Jul 15 17:01:10 amobile ollama[17467]: [GIN] 2025/07/15 - 17:01:10 | 200 |     140.204µs |       127.0.0.1 | GET      "/api/version"
Jul 15 17:02:26 amobile ollama[17467]: [GIN] 2025/07/15 - 17:02:26 | 200 |         1m37s |       127.0.0.1 | POST     "/api/chat"
Jul 15 17:35:05 amobile ollama[17467]: [GIN] 2025/07/15 - 17:35:05 | 200 |      52.773µs |       127.0.0.1 | HEAD     "/"
Jul 15 17:35:05 amobile ollama[17467]: [GIN] 2025/07/15 - 17:35:05 | 200 |  204.188719ms |       127.0.0.1 | POST     "/api/show"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.674-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.676-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 36275"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.788-04:00 level=INFO source=runner.go:925 msg="starting ollama engine"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.790-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:36275"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.880-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36
Jul 15 17:35:05 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.888-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU"
Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB"
Jul 15 17:35:06 amobile ollama[17467]: time=2025-07-15T17:35:06.025-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Jul 15 17:35:06 amobile ollama[17467]: time=2025-07-15T17:35:06.174-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 17:35:06 amobile ollama[17467]: time=2025-07-15T17:35:06.447-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB"
Jul 15 17:35:08 amobile ollama[17467]: time=2025-07-15T17:35:08.049-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.27 seconds"
Jul 15 17:35:08 amobile ollama[17467]: [GIN] 2025/07/15 - 17:35:08 | 200 |  2.657473117s |       127.0.0.1 | POST     "/api/generate"
Jul 15 17:39:08 amobile ollama[17467]: [GIN] 2025/07/15 - 17:39:08 | 200 |          2m2s |       127.0.0.1 | POST     "/api/chat"
Jul 15 17:41:57 amobile ollama[17467]: [GIN] 2025/07/15 - 17:41:57 | 200 | 42.836773699s |       127.0.0.1 | POST     "/api/chat"
Jul 15 17:43:41 amobile ollama[17467]: [GIN] 2025/07/15 - 17:43:41 | 200 | 31.474378088s |       127.0.0.1 | POST     "/api/chat"
<!-- gh-comment-id:3075945773 --> @abcbarryn commented on GitHub (Jul 15, 2025): ``` Jul 15 01:06:05 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:05 | 200 | 43.89µs | 127.0.0.1 | HEAD "/" Jul 15 01:06:05 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:05 | 200 | 34.607µs | 127.0.0.1 | GET "/api/ps" Jul 15 01:06:15 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:15 | 200 | 34.303µs | 127.0.0.1 | HEAD "/" Jul 15 01:06:15 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:15 | 200 | 199.449466ms | 127.0.0.1 | POST "/api/show" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.135-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.7 GiB" free_swap="29.7 GiB" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.138-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.236-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 33357" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.237-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.237-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.237-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.253-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.254-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:33357" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.344-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 01:06:16 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.351-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.357-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.489-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.666-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 01:06:16 amobile ollama[17467]: time=2025-07-15T01:06:16.962-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 01:06:17 amobile ollama[17467]: time=2025-07-15T01:06:17.762-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.53 seconds" Jul 15 01:06:17 amobile ollama[17467]: [GIN] 2025/07/15 - 01:06:17 | 200 | 1.92506674s | 127.0.0.1 | POST "/api/generate" Jul 15 01:09:41 amobile ollama[17467]: [GIN] 2025/07/15 - 01:09:41 | 200 | 2m42s | 127.0.0.1 | POST "/api/chat" Jul 15 01:12:48 amobile ollama[17467]: [GIN] 2025/07/15 - 01:12:48 | 200 | 2m0s | 127.0.0.1 | POST "/api/chat" Jul 15 01:19:34 amobile ollama[17467]: [GIN] 2025/07/15 - 01:19:34 | 200 | 2m42s | 127.0.0.1 | POST "/api/chat" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.026-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.029-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41521" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.148-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.149-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.168-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.168-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:41521" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.273-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 01:24:42 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.280-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.285-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.286-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.286-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.286-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.401-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.570-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 01:24:42 amobile ollama[17467]: time=2025-07-15T01:24:42.747-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 01:24:43 amobile ollama[17467]: time=2025-07-15T01:24:43.911-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.76 seconds" Jul 15 01:27:35 amobile ollama[17467]: [GIN] 2025/07/15 - 01:27:35 | 200 | 2m53s | 127.0.0.1 | POST "/api/chat" Jul 15 01:33:05 amobile ollama[17467]: [GIN] 2025/07/15 - 01:33:05 | 200 | 37.98540726s | 127.0.0.1 | POST "/api/chat" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.619-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.621-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.716-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41437" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.716-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.716-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.717-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.734-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.736-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:41437" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.827-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 01:40:16 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.834-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.841-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 01:40:16 amobile ollama[17467]: time=2025-07-15T01:40:16.968-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 01:40:17 amobile ollama[17467]: time=2025-07-15T01:40:17.113-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 01:40:17 amobile ollama[17467]: time=2025-07-15T01:40:17.288-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 01:40:18 amobile ollama[17467]: time=2025-07-15T01:40:18.226-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.51 seconds" Jul 15 01:41:38 amobile ollama[17467]: [GIN] 2025/07/15 - 01:41:38 | 200 | 1m22s | 127.0.0.1 | POST "/api/chat" Jul 15 01:44:40 amobile ollama[17467]: [GIN] 2025/07/15 - 01:44:40 | 200 | 1m3s | 127.0.0.1 | POST "/api/chat" Jul 15 01:49:32 amobile ollama[17467]: [GIN] 2025/07/15 - 01:49:32 | 200 | 26.3552658s | 127.0.0.1 | POST "/api/chat" Jul 15 02:00:49 amobile ollama[17467]: [GIN] 2025/07/15 - 02:00:49 | 200 | 39.415µs | 127.0.0.1 | HEAD "/" Jul 15 02:00:49 amobile ollama[17467]: [GIN] 2025/07/15 - 02:00:49 | 200 | 182.084631ms | 127.0.0.1 | POST "/api/show" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.063-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.6 GiB" free_swap="29.7 GiB" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.065-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.166-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 45897" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.167-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.167-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.167-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.185-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.185-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:45897" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.274-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 02:00:50 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.281-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.286-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.287-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.287-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.287-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.419-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.575-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 02:00:50 amobile ollama[17467]: time=2025-07-15T02:00:50.848-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 02:00:51 amobile ollama[17467]: time=2025-07-15T02:00:51.684-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.52 seconds" Jul 15 02:00:51 amobile ollama[17467]: [GIN] 2025/07/15 - 02:00:51 | 200 | 1.910645146s | 127.0.0.1 | POST "/api/generate" Jul 15 02:04:07 amobile ollama[17467]: [GIN] 2025/07/15 - 02:04:07 | 200 | 2m49s | 127.0.0.1 | POST "/api/chat" Jul 15 02:06:47 amobile ollama[17467]: [GIN] 2025/07/15 - 02:06:47 | 200 | 2m12s | 127.0.0.1 | POST "/api/chat" Jul 15 02:10:37 amobile ollama[17467]: [GIN] 2025/07/15 - 02:10:37 | 200 | 2m24s | 127.0.0.1 | POST "/api/chat" Jul 15 02:13:36 amobile ollama[17467]: [GIN] 2025/07/15 - 02:13:36 | 200 | 1m45s | 127.0.0.1 | POST "/api/chat" Jul 15 02:18:37 amobile ollama[17467]: [GIN] 2025/07/15 - 02:18:37 | 200 | 1m29s | 127.0.0.1 | POST "/api/chat" Jul 15 02:20:22 amobile ollama[17467]: [GIN] 2025/07/15 - 02:20:22 | 200 | 24.101449501s | 127.0.0.1 | POST "/api/chat" Jul 15 02:22:28 amobile ollama[17467]: [GIN] 2025/07/15 - 02:22:28 | 200 | 1m16s | 127.0.0.1 | POST "/api/chat" Jul 15 02:24:37 amobile ollama[17467]: [GIN] 2025/07/15 - 02:24:37 | 200 | 1m15s | 127.0.0.1 | POST "/api/chat" Jul 15 02:26:57 amobile ollama[17467]: [GIN] 2025/07/15 - 02:26:57 | 200 | 1m14s | 127.0.0.1 | POST "/api/chat" Jul 15 02:31:07 amobile ollama[17467]: [GIN] 2025/07/15 - 02:31:07 | 200 | 2m13s | 127.0.0.1 | POST "/api/chat" Jul 15 02:32:33 amobile ollama[17467]: [GIN] 2025/07/15 - 02:32:33 | 200 | 11.564672162s | 127.0.0.1 | POST "/api/chat" Jul 15 02:36:32 amobile ollama[17467]: [GIN] 2025/07/15 - 02:36:32 | 200 | 2m21s | 127.0.0.1 | POST "/api/chat" Jul 15 02:41:53 amobile ollama[17467]: [GIN] 2025/07/15 - 02:41:53 | 200 | 46.782257017s | 127.0.0.1 | POST "/api/chat" Jul 15 02:43:59 amobile ollama[17467]: [GIN] 2025/07/15 - 02:43:59 | 200 | 1m3s | 127.0.0.1 | POST "/api/chat" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.463-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.0 GiB" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.465-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.561-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 41967" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.562-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.562-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.562-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.577-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.577-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:41967" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.664-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 10:58:17 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.671-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.677-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.814-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 10:58:17 amobile ollama[17467]: time=2025-07-15T10:58:17.966-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 10:58:18 amobile ollama[17467]: time=2025-07-15T10:58:18.140-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 10:58:19 amobile ollama[17467]: time=2025-07-15T10:58:19.581-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds" Jul 15 10:58:23 amobile ollama[17467]: [GIN] 2025/07/15 - 10:58:23 | 200 | 6.619394623s | 127.0.0.1 | POST "/api/chat" Jul 15 10:58:51 amobile ollama[17467]: [GIN] 2025/07/15 - 10:58:51 | 200 | 2.678771024s | 127.0.0.1 | POST "/api/chat" Jul 15 10:59:28 amobile ollama[17467]: [GIN] 2025/07/15 - 10:59:28 | 200 | 16.793880245s | 127.0.0.1 | POST "/api/chat" Jul 15 11:01:09 amobile ollama[17467]: [GIN] 2025/07/15 - 11:01:09 | 200 | 5.583076216s | 127.0.0.1 | POST "/api/chat" Jul 15 12:24:46 amobile ollama[17467]: [GIN] 2025/07/15 - 12:24:46 | 200 | 56.614µs | 127.0.0.1 | HEAD "/" Jul 15 12:24:46 amobile ollama[17467]: [GIN] 2025/07/15 - 12:24:46 | 200 | 187.47452ms | 127.0.0.1 | POST "/api/show" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.225-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.0 GiB" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.227-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 38447" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.325-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.340-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.341-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:38447" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.430-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 12:24:47 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.437-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.443-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.576-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 12:24:47 amobile ollama[17467]: time=2025-07-15T12:24:47.743-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 12:24:48 amobile ollama[17467]: time=2025-07-15T12:24:48.011-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 12:24:49 amobile ollama[17467]: time=2025-07-15T12:24:49.594-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.27 seconds" Jul 15 12:24:49 amobile ollama[17467]: [GIN] 2025/07/15 - 12:24:49 | 200 | 2.646873422s | 127.0.0.1 | POST "/api/generate" Jul 15 12:28:09 amobile ollama[17467]: [GIN] 2025/07/15 - 12:28:09 | 200 | 2m41s | 127.0.0.1 | POST "/api/chat" Jul 15 12:30:20 amobile ollama[17467]: [GIN] 2025/07/15 - 12:30:20 | 200 | 46.245741541s | 127.0.0.1 | POST "/api/chat" Jul 15 12:31:18 amobile ollama[17467]: [GIN] 2025/07/15 - 12:31:18 | 200 | 40.434622179s | 127.0.0.1 | POST "/api/chat" Jul 15 12:32:04 amobile ollama[17467]: [GIN] 2025/07/15 - 12:32:04 | 200 | 11.571502803s | 127.0.0.1 | POST "/api/chat" Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.853-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.3 GiB" free_swap="30.1 GiB" Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.855-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 43873" Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.955-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.975-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 14:05:59 amobile ollama[17467]: time=2025-07-15T14:05:59.976-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:43873" Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.077-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 14:06:00 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.084-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.090-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.207-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.381-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 14:06:00 amobile ollama[17467]: time=2025-07-15T14:06:00.559-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 14:06:01 amobile ollama[17467]: time=2025-07-15T14:06:01.977-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds" Jul 15 14:06:14 amobile ollama[17467]: [GIN] 2025/07/15 - 14:06:14 | 200 | 15.243695865s | 127.0.0.1 | POST "/api/chat" Jul 15 14:08:49 amobile ollama[17467]: [GIN] 2025/07/15 - 14:08:49 | 200 | 7.81688474s | 127.0.0.1 | POST "/api/chat" Jul 15 14:10:32 amobile ollama[17467]: [GIN] 2025/07/15 - 14:10:32 | 200 | 5.57302473s | 127.0.0.1 | POST "/api/chat" Jul 15 14:11:52 amobile ollama[17467]: [GIN] 2025/07/15 - 14:11:52 | 200 | 4.563861397s | 127.0.0.1 | POST "/api/chat" Jul 15 14:12:21 amobile ollama[17467]: [GIN] 2025/07/15 - 14:12:21 | 200 | 7.445482222s | 127.0.0.1 | POST "/api/chat" Jul 15 14:13:40 amobile ollama[17467]: [GIN] 2025/07/15 - 14:13:40 | 200 | 8.141572187s | 127.0.0.1 | POST "/api/chat" Jul 15 14:15:38 amobile ollama[17467]: [GIN] 2025/07/15 - 14:15:38 | 200 | 11.704692526s | 127.0.0.1 | POST "/api/chat" Jul 15 14:17:23 amobile ollama[17467]: [GIN] 2025/07/15 - 14:17:23 | 200 | 8.167364087s | 127.0.0.1 | POST "/api/chat" Jul 15 14:19:24 amobile ollama[17467]: [GIN] 2025/07/15 - 14:19:24 | 200 | 8.725596273s | 127.0.0.1 | POST "/api/chat" Jul 15 14:20:54 amobile ollama[17467]: [GIN] 2025/07/15 - 14:20:54 | 200 | 7.287166608s | 127.0.0.1 | POST "/api/chat" Jul 15 14:23:09 amobile ollama[17467]: [GIN] 2025/07/15 - 14:23:09 | 200 | 7.923928608s | 127.0.0.1 | POST "/api/chat" Jul 15 14:28:00 amobile ollama[17467]: [GIN] 2025/07/15 - 14:28:00 | 200 | 9.638210214s | 127.0.0.1 | POST "/api/chat" Jul 15 14:30:20 amobile ollama[17467]: [GIN] 2025/07/15 - 14:30:20 | 200 | 11.398374606s | 127.0.0.1 | POST "/api/chat" Jul 15 14:32:11 amobile ollama[17467]: [GIN] 2025/07/15 - 14:32:11 | 200 | 6.043563297s | 127.0.0.1 | POST "/api/chat" Jul 15 14:35:04 amobile ollama[17467]: [GIN] 2025/07/15 - 14:35:04 | 200 | 10.856669259s | 127.0.0.1 | POST "/api/chat" Jul 15 14:38:09 amobile ollama[17467]: [GIN] 2025/07/15 - 14:38:09 | 200 | 10.15686096s | 127.0.0.1 | POST "/api/chat" Jul 15 14:39:15 amobile ollama[17467]: [GIN] 2025/07/15 - 14:39:15 | 200 | 6.940100831s | 127.0.0.1 | POST "/api/chat" Jul 15 14:41:27 amobile ollama[17467]: [GIN] 2025/07/15 - 14:41:27 | 200 | 12.226914926s | 127.0.0.1 | POST "/api/chat" Jul 15 14:44:28 amobile ollama[17467]: [GIN] 2025/07/15 - 14:44:28 | 200 | 23.563901162s | 127.0.0.1 | POST "/api/chat" Jul 15 14:48:26 amobile ollama[17467]: [GIN] 2025/07/15 - 14:48:26 | 200 | 33.467552018s | 127.0.0.1 | POST "/api/chat" Jul 15 14:50:38 amobile ollama[17467]: [GIN] 2025/07/15 - 14:50:38 | 200 | 32.005724467s | 127.0.0.1 | POST "/api/chat" Jul 15 14:52:51 amobile ollama[17467]: [GIN] 2025/07/15 - 14:52:51 | 200 | 34.606237099s | 127.0.0.1 | POST "/api/chat" Jul 15 14:55:03 amobile ollama[17467]: [GIN] 2025/07/15 - 14:55:03 | 200 | 39.147461074s | 127.0.0.1 | POST "/api/chat" Jul 15 14:57:11 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:11 | 200 | 37.597258006s | 127.0.0.1 | POST "/api/chat" Jul 15 14:57:45 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:45 | 200 | 60.643µs | 127.0.0.1 | HEAD "/" Jul 15 14:57:45 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:45 | 200 | 75.829µs | 127.0.0.1 | GET "/api/ps" Jul 15 14:57:49 amobile ollama[17467]: [GIN] 2025/07/15 - 14:57:49 | 200 | 5.326923899s | 127.0.0.1 | POST "/api/chat" Jul 15 14:58:40 amobile ollama[17467]: [GIN] 2025/07/15 - 14:58:40 | 200 | 39.146µs | 127.0.0.1 | HEAD "/" Jul 15 14:58:40 amobile ollama[17467]: [GIN] 2025/07/15 - 14:58:40 | 200 | 37.34µs | 127.0.0.1 | GET "/api/ps" Jul 15 15:31:24 amobile ollama[17467]: [GIN] 2025/07/15 - 15:31:24 | 200 | 39.551µs | 127.0.0.1 | HEAD "/" Jul 15 15:31:24 amobile ollama[17467]: [GIN] 2025/07/15 - 15:31:24 | 200 | 193.354766ms | 127.0.0.1 | POST "/api/show" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.125-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.127-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 35539" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.223-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.237-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.237-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:35539" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.331-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 15:31:25 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.337-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.343-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.475-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.638-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 15:31:25 amobile ollama[17467]: time=2025-07-15T15:31:25.913-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 15:31:27 amobile ollama[17467]: time=2025-07-15T15:31:27.248-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds" Jul 15 15:31:27 amobile ollama[17467]: [GIN] 2025/07/15 - 15:31:27 | 200 | 2.458372036s | 127.0.0.1 | POST "/api/generate" Jul 15 15:32:06 amobile ollama[17467]: [GIN] 2025/07/15 - 15:32:06 | 200 | 12.149772723s | 127.0.0.1 | POST "/api/chat" Jul 15 15:32:50 amobile ollama[17467]: [GIN] 2025/07/15 - 15:32:50 | 200 | 19.018623689s | 127.0.0.1 | POST "/api/chat" Jul 15 15:33:40 amobile ollama[17467]: [GIN] 2025/07/15 - 15:33:40 | 200 | 19.08334206s | 127.0.0.1 | POST "/api/chat" Jul 15 15:34:59 amobile ollama[17467]: [GIN] 2025/07/15 - 15:34:59 | 200 | 26.413488556s | 127.0.0.1 | POST "/api/chat" Jul 15 15:37:22 amobile ollama[17467]: [GIN] 2025/07/15 - 15:37:22 | 200 | 27.871657486s | 127.0.0.1 | POST "/api/chat" Jul 15 15:38:35 amobile ollama[17467]: [GIN] 2025/07/15 - 15:38:35 | 200 | 27.072325445s | 127.0.0.1 | POST "/api/chat" Jul 15 15:40:25 amobile ollama[17467]: [GIN] 2025/07/15 - 15:40:25 | 200 | 38.748835117s | 127.0.0.1 | POST "/api/chat" Jul 15 15:42:57 amobile ollama[17467]: [GIN] 2025/07/15 - 15:42:57 | 200 | 3.887759995s | 127.0.0.1 | POST "/api/chat" Jul 15 15:47:15 amobile ollama[17467]: [GIN] 2025/07/15 - 15:47:15 | 200 | 32.823251665s | 127.0.0.1 | POST "/api/chat" Jul 15 15:47:48 amobile ollama[17467]: [GIN] 2025/07/15 - 15:47:48 | 200 | 8.797014247s | 127.0.0.1 | POST "/api/chat" Jul 15 15:48:16 amobile ollama[17467]: [GIN] 2025/07/15 - 15:48:16 | 200 | 23.792104523s | 127.0.0.1 | POST "/api/chat" Jul 15 15:48:38 amobile ollama[17467]: [GIN] 2025/07/15 - 15:48:38 | 200 | 9.21259348s | 127.0.0.1 | POST "/api/chat" Jul 15 15:49:31 amobile ollama[17467]: [GIN] 2025/07/15 - 15:49:31 | 200 | 21.710448987s | 127.0.0.1 | POST "/api/chat" Jul 15 15:49:35 amobile ollama[17467]: [GIN] 2025/07/15 - 15:49:35 | 200 | 32.825344864s | 127.0.0.1 | POST "/api/chat" Jul 15 15:49:40 amobile ollama[17467]: [GIN] 2025/07/15 - 15:49:40 | 200 | 7.626245474s | 127.0.0.1 | POST "/api/chat" Jul 15 15:50:47 amobile ollama[17467]: [GIN] 2025/07/15 - 15:50:47 | 200 | 6.319395124s | 127.0.0.1 | POST "/api/chat" Jul 15 15:50:55 amobile ollama[17467]: [GIN] 2025/07/15 - 15:50:55 | 200 | 16.482319877s | 127.0.0.1 | POST "/api/chat" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.011-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.1 GiB" free_swap="30.1 GiB" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.013-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.108-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 40683" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.108-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.109-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.109-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.136-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.136-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:40683" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.233-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 16:00:37 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.240-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.245-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.361-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.537-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:00:37 amobile ollama[17467]: time=2025-07-15T16:00:37.714-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:00:39 amobile ollama[17467]: time=2025-07-15T16:00:39.125-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.02 seconds" Jul 15 16:00:50 amobile ollama[17467]: [GIN] 2025/07/15 - 16:00:50 | 200 | 13.453382374s | 127.0.0.1 | POST "/api/chat" Jul 15 16:01:37 amobile ollama[17467]: [GIN] 2025/07/15 - 16:01:37 | 200 | 7.010397526s | 127.0.0.1 | POST "/api/chat" Jul 15 16:02:47 amobile ollama[17467]: [GIN] 2025/07/15 - 16:02:47 | 200 | 9.218088928s | 127.0.0.1 | POST "/api/chat" Jul 15 16:03:40 amobile ollama[17467]: [GIN] 2025/07/15 - 16:03:40 | 200 | 8.419104993s | 127.0.0.1 | POST "/api/chat" Jul 15 16:06:18 amobile ollama[17467]: [GIN] 2025/07/15 - 16:06:18 | 200 | 44.640608373s | 127.0.0.1 | POST "/api/chat" Jul 15 16:06:50 amobile ollama[17467]: [GIN] 2025/07/15 - 16:06:50 | 200 | 17.14751161s | 127.0.0.1 | POST "/api/chat" Jul 15 16:07:39 amobile ollama[17467]: [GIN] 2025/07/15 - 16:07:39 | 200 | 38.689371786s | 127.0.0.1 | POST "/api/chat" Jul 15 16:08:12 amobile ollama[17467]: [GIN] 2025/07/15 - 16:08:12 | 200 | 32.899070555s | 127.0.0.1 | POST "/api/chat" Jul 15 16:08:34 amobile ollama[17467]: time=2025-07-15T16:08:34.345-04:00 level=WARN source=runner.go:157 msg="truncating input prompt" limit=4096 prompt=19010 keep=4 new=4096 Jul 15 16:09:46 amobile ollama[17467]: [GIN] 2025/07/15 - 16:09:46 | 200 | 25.107300894s | 127.0.0.1 | POST "/api/chat" Jul 15 16:12:18 amobile ollama[17467]: [GIN] 2025/07/15 - 16:12:18 | 200 | 3m43s | 127.0.0.1 | POST "/api/chat" Jul 15 16:12:19 amobile ollama[17467]: [GIN] 2025/07/15 - 16:12:19 | 200 | 1m36s | 127.0.0.1 | POST "/api/chat" Jul 15 16:15:05 amobile ollama[17467]: [GIN] 2025/07/15 - 16:15:05 | 200 | 1m53s | 127.0.0.1 | POST "/api/chat" Jul 15 16:15:38 amobile ollama[17467]: [GIN] 2025/07/15 - 16:15:38 | 200 | 1m14s | 127.0.0.1 | POST "/api/chat" Jul 15 16:15:48 amobile ollama[17467]: [GIN] 2025/07/15 - 16:15:48 | 200 | 33.070491476s | 127.0.0.1 | POST "/api/chat" Jul 15 16:17:31 amobile ollama[17467]: [GIN] 2025/07/15 - 16:17:31 | 200 | 1m0s | 127.0.0.1 | POST "/api/chat" Jul 15 16:21:06 amobile ollama[17467]: [GIN] 2025/07/15 - 16:21:06 | 200 | 34.303595005s | 127.0.0.1 | POST "/api/chat" Jul 15 16:21:32 amobile ollama[17467]: panic: failed to decode batch: could not find a kv cache slot (cache: 2560 batch: 512) Jul 15 16:21:32 amobile ollama[17467]: goroutine 8 [running]: Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002b6900, {0x55867a095700, 0xc0000008c0}) Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x65 Jul 15 16:21:32 amobile ollama[17467]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74 Jul 15 16:21:32 amobile ollama[17467]: time=2025-07-15T16:21:32.337-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:40683/completion\": EOF" Jul 15 16:21:32 amobile ollama[17467]: [GIN] 2025/07/15 - 16:21:32 | 500 | 11.994152362s | 127.0.0.1 | POST "/api/chat" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.458-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.461-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.562-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 45949" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.562-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.562-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.563-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.581-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.582-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:45949" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.678-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 16:22:39 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.684-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.690-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.814-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 16:22:39 amobile ollama[17467]: time=2025-07-15T16:22:39.973-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:22:40 amobile ollama[17467]: time=2025-07-15T16:22:40.238-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:22:41 amobile ollama[17467]: time=2025-07-15T16:22:41.844-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.28 seconds" Jul 15 16:23:21 amobile ollama[17467]: [GIN] 2025/07/15 - 16:23:21 | 200 | 42.358125818s | 127.0.0.1 | POST "/api/chat" Jul 15 16:35:49 amobile ollama[17467]: time=2025-07-15T16:35:49.962-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB" Jul 15 16:35:49 amobile ollama[17467]: time=2025-07-15T16:35:49.964-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.062-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 36385" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.062-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.063-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.063-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.080-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.081-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:36385" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.178-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 16:35:50 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.186-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.193-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.314-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.481-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:35:50 amobile ollama[17467]: time=2025-07-15T16:35:50.656-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:35:52 amobile ollama[17467]: time=2025-07-15T16:35:52.094-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.03 seconds" Jul 15 16:36:34 amobile ollama[17467]: [GIN] 2025/07/15 - 16:36:34 | 200 | 44.698539465s | 127.0.0.1 | POST "/api/chat" Jul 15 16:37:39 amobile ollama[17467]: [GIN] 2025/07/15 - 16:37:39 | 200 | 15.367562581s | 127.0.0.1 | POST "/api/chat" Jul 15 16:39:19 amobile ollama[17467]: [GIN] 2025/07/15 - 16:39:19 | 200 | 58.985695818s | 127.0.0.1 | POST "/api/chat" Jul 15 16:39:26 amobile ollama[17467]: [GIN] 2025/07/15 - 16:39:26 | 200 | 1m4s | 127.0.0.1 | POST "/api/chat" Jul 15 16:40:27 amobile ollama[17467]: [GIN] 2025/07/15 - 16:40:27 | 200 | 32.498111154s | 127.0.0.1 | POST "/api/chat" Jul 15 16:41:19 amobile ollama[17467]: [GIN] 2025/07/15 - 16:41:19 | 200 | 25.790679315s | 127.0.0.1 | POST "/api/chat" Jul 15 16:42:42 amobile ollama[17467]: [GIN] 2025/07/15 - 16:42:42 | 200 | 29.962983809s | 127.0.0.1 | POST "/api/chat" Jul 15 16:44:26 amobile ollama[17467]: [GIN] 2025/07/15 - 16:44:26 | 200 | 20.049622997s | 127.0.0.1 | POST "/api/chat" Jul 15 16:45:03 amobile ollama[17467]: [GIN] 2025/07/15 - 16:45:03 | 200 | 11.432715593s | 127.0.0.1 | POST "/api/chat" Jul 15 16:45:30 amobile ollama[17467]: [GIN] 2025/07/15 - 16:45:30 | 200 | 15.81967878s | 127.0.0.1 | POST "/api/chat" Jul 15 16:47:41 amobile ollama[17467]: [GIN] 2025/07/15 - 16:47:41 | 200 | 1m15s | 127.0.0.1 | POST "/api/chat" Jul 15 16:49:29 amobile ollama[17467]: [GIN] 2025/07/15 - 16:49:29 | 200 | 3m9s | 127.0.0.1 | POST "/api/chat" Jul 15 16:51:05 amobile ollama[17467]: [GIN] 2025/07/15 - 16:51:05 | 200 | 14.459985878s | 127.0.0.1 | POST "/api/chat" Jul 15 16:52:31 amobile ollama[17467]: panic: failed to decode batch: could not find a kv cache slot (cache: 2560 batch: 512) Jul 15 16:52:31 amobile ollama[17467]: goroutine 14 [running]: Jul 15 16:52:31 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc00065e900, {0x555e3641c700, 0xc0001308c0}) Jul 15 16:52:31 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x65 Jul 15 16:52:31 amobile ollama[17467]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 Jul 15 16:52:31 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74 Jul 15 16:52:31 amobile ollama[17467]: time=2025-07-15T16:52:31.866-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:36385/completion\": EOF" Jul 15 16:52:31 amobile ollama[17467]: [GIN] 2025/07/15 - 16:52:31 | 200 | 13.142628839s | 127.0.0.1 | POST "/api/chat" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.611-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.613-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 39263" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.724-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.739-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.740-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:39263" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.836-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 16:53:23 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.842-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.848-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 16:53:23 amobile ollama[17467]: time=2025-07-15T16:53:23.976-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 16:53:24 amobile ollama[17467]: time=2025-07-15T16:53:24.139-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:53:24 amobile ollama[17467]: time=2025-07-15T16:53:24.409-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 16:53:26 amobile ollama[17467]: time=2025-07-15T16:53:26.009-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.28 seconds" Jul 15 16:54:38 amobile ollama[17467]: [GIN] 2025/07/15 - 16:54:38 | 200 | 1m15s | 127.0.0.1 | POST "/api/chat" Jul 15 16:56:20 amobile ollama[17467]: [GIN] 2025/07/15 - 16:56:20 | 200 | 1m9s | 127.0.0.1 | POST "/api/chat" Jul 15 16:59:05 amobile ollama[17467]: [GIN] 2025/07/15 - 16:59:05 | 200 | 1m34s | 127.0.0.1 | POST "/api/chat" Jul 15 17:00:40 amobile ollama[17467]: [GIN] 2025/07/15 - 17:00:40 | 200 | 1m33s | 127.0.0.1 | POST "/api/chat" Jul 15 17:01:10 amobile ollama[17467]: [GIN] 2025/07/15 - 17:01:10 | 200 | 140.204µs | 127.0.0.1 | GET "/api/version" Jul 15 17:02:26 amobile ollama[17467]: [GIN] 2025/07/15 - 17:02:26 | 200 | 1m37s | 127.0.0.1 | POST "/api/chat" Jul 15 17:35:05 amobile ollama[17467]: [GIN] 2025/07/15 - 17:35:05 | 200 | 52.773µs | 127.0.0.1 | HEAD "/" Jul 15 17:35:05 amobile ollama[17467]: [GIN] 2025/07/15 - 17:35:05 | 200 | 204.188719ms | 127.0.0.1 | POST "/api/show" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.674-04:00 level=INFO source=server.go:135 msg="system memory" total="31.2 GiB" free="27.2 GiB" free_swap="30.1 GiB" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.676-04:00 level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[27.2 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="450.0 MiB" memory.required.allocations="[5.1 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="1.8 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="517.0 MiB" memory.graph.partial="1.0 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/local/bin/ollama runner --ollama-engine --model /usr/share/ollama/.ollama/models/blobs/sha256-aeda25e63ebd698fab8638ffb778e68bed908b960d39d0becc650fa981609d25 --ctx-size 8192 --batch-size 512 --threads 28 --no-mmap --parallel 2 --port 36275" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.774-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.788-04:00 level=INFO source=runner.go:925 msg="starting ollama engine" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.790-04:00 level=INFO source=runner.go:983 msg="Server listening on 127.0.0.1:36275" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.880-04:00 level=INFO source=ggml.go:92 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=36 Jul 15 17:35:05 amobile ollama[17467]: load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.888-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:359 msg="offloading 0 repeating layers to GPU" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:363 msg="offloading output layer to CPU" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:375 msg="offloaded 0/35 layers to GPU" Jul 15 17:35:05 amobile ollama[17467]: time=2025-07-15T17:35:05.893-04:00 level=INFO source=ggml.go:377 msg="model weights" buffer=CPU size="3.6 GiB" Jul 15 17:35:06 amobile ollama[17467]: time=2025-07-15T17:35:06.025-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" Jul 15 17:35:06 amobile ollama[17467]: time=2025-07-15T17:35:06.174-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 17:35:06 amobile ollama[17467]: time=2025-07-15T17:35:06.447-04:00 level=INFO source=ggml.go:666 msg="compute graph" backend=CPU buffer_type=CPU size="1.1 GiB" Jul 15 17:35:08 amobile ollama[17467]: time=2025-07-15T17:35:08.049-04:00 level=INFO source=server.go:637 msg="llama runner started in 2.27 seconds" Jul 15 17:35:08 amobile ollama[17467]: [GIN] 2025/07/15 - 17:35:08 | 200 | 2.657473117s | 127.0.0.1 | POST "/api/generate" Jul 15 17:39:08 amobile ollama[17467]: [GIN] 2025/07/15 - 17:39:08 | 200 | 2m2s | 127.0.0.1 | POST "/api/chat" Jul 15 17:41:57 amobile ollama[17467]: [GIN] 2025/07/15 - 17:41:57 | 200 | 42.836773699s | 127.0.0.1 | POST "/api/chat" Jul 15 17:43:41 amobile ollama[17467]: [GIN] 2025/07/15 - 17:43:41 | 200 | 31.474378088s | 127.0.0.1 | POST "/api/chat" ```
GiteaMirror commented 2026-04-29 05:10:15 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 15, 2025):

Jul 15 16:21:32 amobile ollama[17467]: panic: failed to decode batch: could not find a kv cache slot (cache: 2560 batch: 512)
Jul 15 16:21:32 amobile ollama[17467]: goroutine 8 [running]:
Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002b6900, {0x55867a095700, 0xc0000008c0})
Jul 15 16:21:32 amobile ollama[17467]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x65
Jul 15 16:21:32 amobile ollama[17467]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
Jul 15 16:21:32 amobile ollama[17467]:         github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74
Jul 15 16:21:32 amobile ollama[17467]: time=2025-07-15T16:21:32.337-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:40683/completion\": EOF"

Could be #10127. A workaround is to set OLLAMA_NUM_PARALLEL=1.

<!-- gh-comment-id:3075958270 --> @rick-github commented on GitHub (Jul 15, 2025): ``` Jul 15 16:21:32 amobile ollama[17467]: panic: failed to decode batch: could not find a kv cache slot (cache: 2560 batch: 512) Jul 15 16:21:32 amobile ollama[17467]: goroutine 8 [running]: Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0002b6900, {0x55867a095700, 0xc0000008c0}) Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x65 Jul 15 16:21:32 amobile ollama[17467]: created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 Jul 15 16:21:32 amobile ollama[17467]: github.com/ollama/ollama/runner/ollamarunner/runner.go:960 +0xa74 Jul 15 16:21:32 amobile ollama[17467]: time=2025-07-15T16:21:32.337-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:40683/completion\": EOF" ``` Could be #10127. A workaround is to set `OLLAMA_NUM_PARALLEL=1`.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#54061
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?