github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #12900] MacOS Ollama Memory Hang #8549

New Issue
Closed
opened 2026-04-12 21:15:46 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 21:15:46 -05:00
Owner
Copy Link

Originally created by @josephlugo on GitHub (Nov 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12900

What is the issue?

So, this happens with the latest version of Ollama now:

After using Ollama for a while inside an automation it suddenly throws an error and this is how the memory in the server stays:

Image

Even closing Ollama daemon won't free up that memory.

I can confirm same exact config in my automation was working just fine before the last two releases.

Relevant log output

time=2025-11-01T09:30:02.361-04:00 level=INFO source=ggml.go:104 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 compiler=cgo(clang)
ggml_metal_init: allocating
ggml_metal_init: picking default device: Apple M3 Ultra
ggml_metal_init: use bfloat         = true
ggml_metal_init: use fusion         = true
ggml_metal_init: use concurrency    = true
ggml_metal_init: use graph optimize = true
time=2025-11-01T09:30:02.486-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-01T09:30:02.559-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=ggml.go:482 msg="offloading 43 repeating layers to GPU"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=ggml.go:494 msg="offloaded 43/95 layers to GPU"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:212 msg="model weights" device=Metal size="60.4 GiB"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:217 msg="model weights" device=CPU size="72.0 GiB"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:223 msg="kv cache" device=Metal size="5.4 GiB"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:228 msg="kv cache" device=CPU size="6.4 GiB"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:234 msg="compute graph" device=Metal size="5.6 GiB"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:239 msg="compute graph" device=CPU size="112.0 MiB"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:244 msg="total memory" size="149.8 GiB"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=sched.go:493 msg="loaded runners" count=1
time=2025-11-01T09:30:03.220-04:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding"
time=2025-11-01T09:30:03.220-04:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server loading model"
time=2025-11-01T09:30:25.025-04:00 level=INFO source=server.go:1289 msg="llama runner started in 22.69 seconds"
time=2025-11-01T09:32:18.112-04:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:50588/completion\": EOF"
[GIN] 2025/11/01 - 09:32:18 | 500 |         2m15s |      10.0.4.102 | POST     "/api/chat"
time=2025-11-01T09:32:23.269-04:00 level=INFO source=server.go:215 msg="enabling flash attention"
time=2025-11-01T09:32:23.270-04:00 level=INFO source=server.go:400 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Volumes/ALEF4TB/Ollama/Models/blobs/sha256-791d5d11998e006548d6b58c31756562ea61446ebc7d19686608402a797ecc82 --port 50608"
time=2025-11-01T09:32:23.272-04:00 level=INFO source=server.go:653 msg="loading model" "model layers"=95 requested=-1
time=2025-11-01T09:32:23.272-04:00 level=INFO source=server.go:658 msg="system memory" total="256.0 GiB" free="240.4 GiB" free_swap="0 B"
time=2025-11-01T09:32:23.272-04:00 level=INFO source=server.go:665 msg="gpu memory" id=0 library=Metal available="72.5 GiB" free="73.0 GiB" minimum="512.0 MiB" overhead="0 B"
time=2025-11-01T09:32:23.280-04:00 level=INFO source=runner.go:1349 msg="starting ollama engine"
time=2025-11-01T09:32:23.280-04:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:50608"
time=2025-11-01T09:32:23.284-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:95[ID:0 Layers:95(0..94)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-01T09:32:23.298-04:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3moe file_type=Q4_K_M name="Qwen3 235B A22B Thinking 2507" description="" num_tensors=1131 num_key_values=33
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: loaded in 0.008 sec
ggml_metal_device_init: GPU name:   Apple M3 Ultra
ggml_metal_device_init: GPU family: MTLGPUFamilyApple9  (1009)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4  (5002)
ggml_metal_device_init: simdgroup reduction   = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory    = true
ggml_metal_device_init: has bfloat            = true
ggml_metal_device_init: use residency sets    = true
ggml_metal_device_init: use shared buffers    = true
ggml_metal_device_init: recommendedMaxWorkingSetSize  = 239143.78 MB
time=2025-11-01T09:32:23.300-04:00 level=INFO source=ggml.go:104 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 compiler=cgo(clang)
ggml_metal_init: allocating
ggml_metal_init: picking default device: Apple M3 Ultra
ggml_metal_init: use bfloat         = true
ggml_metal_init: use fusion         = true
ggml_metal_init: use concurrency    = true
ggml_metal_init: use graph optimize = true
time=2025-11-01T09:32:23.493-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-01T09:32:23.565-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-01T09:32:24.204-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-01T09:32:24.204-04:00 level=INFO source=ggml.go:482 msg="offloading 43 repeating layers to GPU"
time=2025-11-01T09:32:24.204-04:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2025-11-01T09:32:24.204-04:00 level=INFO source=ggml.go:494 msg="offloaded 43/95 layers to GPU"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:212 msg="model weights" device=Metal size="60.4 GiB"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:217 msg="model weights" device=CPU size="72.0 GiB"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:223 msg="kv cache" device=Metal size="5.4 GiB"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:228 msg="kv cache" device=CPU size="6.4 GiB"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:234 msg="compute graph" device=Metal size="5.6 GiB"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:239 msg="compute graph" device=CPU size="112.0 MiB"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:244 msg="total memory" size="149.8 GiB"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=sched.go:493 msg="loaded runners" count=1
time=2025-11-01T09:32:24.205-04:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding"
time=2025-11-01T09:32:24.205-04:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server loading model"
time=2025-11-01T09:32:46.261-04:00 level=INFO source=server.go:1289 msg="llama runner started in 22.99 seconds"
time=2025-11-01T09:34:25.049-04:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:50608/completion\": EOF"
[GIN] 2025/11/01 - 09:34:25 | 500 |          2m1s |      10.0.4.102 | POST     "/api/chat"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.12.9

Originally created by @josephlugo on GitHub (Nov 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12900 ### What is the issue? So, this happens with the latest version of Ollama now: After using Ollama for a while inside an automation it suddenly throws an error and this is how the memory in the server stays: <img width="740" height="523" alt="Image" src="https://github.com/user-attachments/assets/ec548c8c-77f4-4ad4-9998-3b631f074ad3" /> Even closing Ollama daemon won't free up that memory. I can confirm same exact config in my automation was working just fine before the last two releases. ### Relevant log output ```shell time=2025-11-01T09:30:02.361-04:00 level=INFO source=ggml.go:104 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 compiler=cgo(clang) ggml_metal_init: allocating ggml_metal_init: picking default device: Apple M3 Ultra ggml_metal_init: use bfloat = true ggml_metal_init: use fusion = true ggml_metal_init: use concurrency = true ggml_metal_init: use graph optimize = true time=2025-11-01T09:30:02.486-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-01T09:30:02.559-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-01T09:30:03.220-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-01T09:30:03.220-04:00 level=INFO source=ggml.go:482 msg="offloading 43 repeating layers to GPU" time=2025-11-01T09:30:03.220-04:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2025-11-01T09:30:03.220-04:00 level=INFO source=ggml.go:494 msg="offloaded 43/95 layers to GPU" time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:212 msg="model weights" device=Metal size="60.4 GiB" time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:217 msg="model weights" device=CPU size="72.0 GiB" time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:223 msg="kv cache" device=Metal size="5.4 GiB" time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:228 msg="kv cache" device=CPU size="6.4 GiB" time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:234 msg="compute graph" device=Metal size="5.6 GiB" time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:239 msg="compute graph" device=CPU size="112.0 MiB" time=2025-11-01T09:30:03.220-04:00 level=INFO source=device.go:244 msg="total memory" size="149.8 GiB" time=2025-11-01T09:30:03.220-04:00 level=INFO source=sched.go:493 msg="loaded runners" count=1 time=2025-11-01T09:30:03.220-04:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding" time=2025-11-01T09:30:03.220-04:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server loading model" time=2025-11-01T09:30:25.025-04:00 level=INFO source=server.go:1289 msg="llama runner started in 22.69 seconds" time=2025-11-01T09:32:18.112-04:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:50588/completion\": EOF" [GIN] 2025/11/01 - 09:32:18 | 500 | 2m15s | 10.0.4.102 | POST "/api/chat" time=2025-11-01T09:32:23.269-04:00 level=INFO source=server.go:215 msg="enabling flash attention" time=2025-11-01T09:32:23.270-04:00 level=INFO source=server.go:400 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Volumes/ALEF4TB/Ollama/Models/blobs/sha256-791d5d11998e006548d6b58c31756562ea61446ebc7d19686608402a797ecc82 --port 50608" time=2025-11-01T09:32:23.272-04:00 level=INFO source=server.go:653 msg="loading model" "model layers"=95 requested=-1 time=2025-11-01T09:32:23.272-04:00 level=INFO source=server.go:658 msg="system memory" total="256.0 GiB" free="240.4 GiB" free_swap="0 B" time=2025-11-01T09:32:23.272-04:00 level=INFO source=server.go:665 msg="gpu memory" id=0 library=Metal available="72.5 GiB" free="73.0 GiB" minimum="512.0 MiB" overhead="0 B" time=2025-11-01T09:32:23.280-04:00 level=INFO source=runner.go:1349 msg="starting ollama engine" time=2025-11-01T09:32:23.280-04:00 level=INFO source=runner.go:1384 msg="Server listening on 127.0.0.1:50608" time=2025-11-01T09:32:23.284-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:95[ID:0 Layers:95(0..94)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-01T09:32:23.298-04:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3moe file_type=Q4_K_M name="Qwen3 235B A22B Thinking 2507" description="" num_tensors=1131 num_key_values=33 ggml_metal_library_init: using embedded metal library ggml_metal_library_init: loaded in 0.008 sec ggml_metal_device_init: GPU name: Apple M3 Ultra ggml_metal_device_init: GPU family: MTLGPUFamilyApple9 (1009) ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003) ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4 (5002) ggml_metal_device_init: simdgroup reduction = true ggml_metal_device_init: simdgroup matrix mul. = true ggml_metal_device_init: has unified memory = true ggml_metal_device_init: has bfloat = true ggml_metal_device_init: use residency sets = true ggml_metal_device_init: use shared buffers = true ggml_metal_device_init: recommendedMaxWorkingSetSize = 239143.78 MB time=2025-11-01T09:32:23.300-04:00 level=INFO source=ggml.go:104 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 compiler=cgo(clang) ggml_metal_init: allocating ggml_metal_init: picking default device: Apple M3 Ultra ggml_metal_init: use bfloat = true ggml_metal_init: use fusion = true ggml_metal_init: use concurrency = true ggml_metal_init: use graph optimize = true time=2025-11-01T09:32:23.493-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-01T09:32:23.565-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-01T09:32:24.204-04:00 level=INFO source=runner.go:1222 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:true KvSize:65536 KvCacheType: NumThreads:20 GPULayers:43[ID:0 Layers:43(51..93)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-01T09:32:24.204-04:00 level=INFO source=ggml.go:482 msg="offloading 43 repeating layers to GPU" time=2025-11-01T09:32:24.204-04:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2025-11-01T09:32:24.204-04:00 level=INFO source=ggml.go:494 msg="offloaded 43/95 layers to GPU" time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:212 msg="model weights" device=Metal size="60.4 GiB" time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:217 msg="model weights" device=CPU size="72.0 GiB" time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:223 msg="kv cache" device=Metal size="5.4 GiB" time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:228 msg="kv cache" device=CPU size="6.4 GiB" time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:234 msg="compute graph" device=Metal size="5.6 GiB" time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:239 msg="compute graph" device=CPU size="112.0 MiB" time=2025-11-01T09:32:24.205-04:00 level=INFO source=device.go:244 msg="total memory" size="149.8 GiB" time=2025-11-01T09:32:24.205-04:00 level=INFO source=sched.go:493 msg="loaded runners" count=1 time=2025-11-01T09:32:24.205-04:00 level=INFO source=server.go:1251 msg="waiting for llama runner to start responding" time=2025-11-01T09:32:24.205-04:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server loading model" time=2025-11-01T09:32:46.261-04:00 level=INFO source=server.go:1289 msg="llama runner started in 22.99 seconds" time=2025-11-01T09:34:25.049-04:00 level=ERROR source=server.go:1475 msg="post predict" error="Post \"http://127.0.0.1:50608/completion\": EOF" [GIN] 2025/11/01 - 09:34:25 | 500 | 2m1s | 10.0.4.102 | POST "/api/chat" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.12.9
GiteaMirror added the memorybug labels 2026-04-12 21:15:46 -05:00
GiteaMirror commented 2026-04-12 21:15:49 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 3, 2025):

Can you please post the log with OLLAMA_DEBUG=1 set? When you say Even closing Ollama daemon won't free up that memory., what did you do exactly and what is the result? Kill the process that is shown in the top of the screen shot?

<!-- gh-comment-id:3482670825 --> @jessegross commented on GitHub (Nov 3, 2025): Can you please post the log with OLLAMA_DEBUG=1 set? When you say `Even closing Ollama daemon won't free up that memory.`, what did you do exactly and what is the result? Kill the process that is shown in the top of the screen shot?
GiteaMirror commented 2026-04-12 21:15:49 -05:00
Author
Owner
Copy Link

@josephlugo commented on GitHub (Nov 4, 2025):

@jessegross Yes, I manually terminated the Ollama process, but the memory usage remained frozen (no graphical movement at all), as shown in the screenshot attached to my initial comment. Only restarting the entire Mac Studio cleared the memory lock.

Unfortunately, I can’t provide updated logs because we rolled the server back to version 0.12.6 to restore normal operation.

<!-- gh-comment-id:3486366829 --> @josephlugo commented on GitHub (Nov 4, 2025): @jessegross Yes, I manually terminated the Ollama process, but the memory usage remained frozen (no graphical movement at all), as shown in the screenshot attached to my initial comment. Only restarting the entire Mac Studio cleared the memory lock. Unfortunately, I can’t provide updated logs because we rolled the server back to version 0.12.6 to restore normal operation.
GiteaMirror commented 2026-04-12 21:15:50 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 5, 2025):

@josephlugo a number of fixes have gone in recently that may intersect with your scenario. Please give 0.12.10 a try and let us know if that resolves the problem, or you still see problems. If you still see problems, please share a server log with the debug logging enabled as described above.

<!-- gh-comment-id:3493685980 --> @dhiltgen commented on GitHub (Nov 5, 2025): @josephlugo a number of fixes have gone in recently that may intersect with your scenario. Please give 0.12.10 a try and let us know if that resolves the problem, or you still see problems. If you still see problems, please share a server log with the debug logging enabled as described above.
GiteaMirror commented 2026-04-12 21:15:50 -05:00
Author
Owner
Copy Link

@josephlugo commented on GitHub (Nov 7, 2025):

@dhiltgen For my use case (65536 context window) 0.12.10 is working perflectly now, speed and all.

Thanks!

<!-- gh-comment-id:3502455186 --> @josephlugo commented on GitHub (Nov 7, 2025): @dhiltgen For my use case (65536 context window) 0.12.10 is working perflectly now, speed and all. Thanks!
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 memory
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#8549
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?