github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14188] Crashes RTX 3060 on cuda_v13 crashes v0.13.0 to v0.15.6 #9247

New Issue
Closed
opened 2026-04-12 22:07:20 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 22:07:20 -05:00
Owner
Copy Link

Originally created by @yunesj on GitHub (Feb 10, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14188

What is the issue?

Ollama crashes RTX 3060 on cuda_v13 crashes v0.13.0 to v0.15.6. Deleting the cuda_v13, backend falls back to cuda_v12, and works, as it did in version <= 0.12.11.

It seems similar to https://github.com/ollama/ollama/pull/12300.

Relevant log output

Feb 10 06:52:34 ollama ollama[5962]: time=2026-02-10T06:52:34.546Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:46567/load\": EOF"
Feb 10 06:52:34 ollama ollama[5962]: time=2026-02-10T06:52:34.546Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:46567/load\": dial tcp 
127.0.0.1:46567: connect: connection refused"
Feb 10 06:52:34 ollama ollama[5962]: time=2026-02-10T06:52:34.546Z level=INFO source=sched.go:490 msg="Load failed" model=/root/.ollama/models/blobs/sha256-a3de86cd1c132c822487e
dedd47a324c50491393e6565cd14bafa40d0b8e686f error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details"
Feb 10 06:52:34 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:34 | 500 |  903.736937ms |       127.0.0.1 | POST     "/api/generate"
Feb 10 06:52:41 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:41 | 200 |      32.665µs |       127.0.0.1 | HEAD     "/"
Feb 10 06:52:41 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:41 | 200 |  129.807248ms |       127.0.0.1 | POST     "/api/show"
Feb 10 06:52:41 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:41 | 200 |  125.652266ms |       127.0.0.1 | POST     "/api/show"
Feb 10 06:52:41 ollama ollama[5962]: time=2026-02-10T06:52:41.952Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/lib/ollama/bin/ollama runner --ollama-en
gine --port 36061"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.156Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsi
ng \"max\": invalid syntax"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=server.go:247 msg="enabling flash attention"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=server.go:431 msg="startFeb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1411 msg="starting ollama engine"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:39333"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.260Z level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAt
tention:Enabled KvSize:4096 KvCacheType: NumThreads:1 GPULayers:37[ID:GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 Us
eMmap:false}"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.290Z level=INFO source=ggml.go:136 msg="" architecture=qwen3 file_type=Q4_K_M name="Qwen3 8B" description="" num_te
nsors=399 num_key_values=29
Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CPU backend from /usr/local/lib/ollama/lib/ollama/libggml-cpu-haswell.so
Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: found 1 CUDA devices:
Feb 10 06:52:42 ollama ollama[5962]:   Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6, VMM: yes, ID: GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14
Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/lib/ollama/cuda_v13/libggml-cuda.so
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.456Z 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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compile
r=cgo(gcc)
Feb 10 06:52:42 ollama ollama[5962]: free(): invalid pointer
Feb 10 06:52:42 ollama ollama[5962]: SIGABRT: abort
Feb 10 06:52:42 ollama ollama[5962]: PC=0x7ccc3749eb2c m=5 sigcode=18446744073709551610
Feb 10 06:52:42 ollama ollama[5962]: signal arrived during cgo execution
Feb 10 06:52:42 ollama ollama[5962]: goroutine 23 gp=0xc000504e00 m=5 mp=0xc000100008 [syscall]:
Feb 10 06:52:42 ollama ollama[5962]: runtime.cgocall(0x65331c7f2d00, 0xc0000490d8)
Feb 10 06:52:42 ollama ollama[5962]:         runtime/cgocall.go:167 +0x4b fp=0xc0000490b0 sp=0xc000049078 pc=0x65331b9a994b
Feb 10 06:52:42 ollama ollama[5962]: github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_reserve(0x7ccbdc79bfd0, 0x7ccb724e4e90)ing runner" cmd="/usr/local/lib/ollama/bin/ollama runner --ollama-en
gine --model /root/.ollama/models/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --port 39333"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=sched.go:463 msg="system memory" total="8.0 GiB" free="107.4 MiB" free_swap="512.0 MiB"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=sched.go:470 msg="gpu memory" id=GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 library=CUDA avail
able="11.2 GiB" free="11.6 GiB" minimum="457.0 MiB" overhead="0 B"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=server.go:757 msg="loading model" "model layers"=37 requested=-1
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1411 msg="starting ollama engine"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:39333"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.260Z level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAt
tention:Enabled KvSize:4096 KvCacheType: NumThreads:1 GPULayers:37[ID:GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 Us
eMmap:false}"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.290Z level=INFO source=ggml.go:136 msg="" architecture=qwen3 file_type=Q4_K_M name="Qwen3 8B" description="" num_te
nsors=399 num_key_values=29
Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CPU backend from /usr/local/lib/ollama/lib/ollama/libggml-cpu-haswell.so
Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: found 1 CUDA devices:
Feb 10 06:52:42 ollama ollama[5962]:   Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6, VMM: yes, ID: GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14
Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/lib/ollama/cuda_v13/libggml-cuda.so
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.456Z 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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compile
r=cgo(gcc)
Feb 10 06:52:42 ollama ollama[5962]: free(): invalid pointer
Feb 10 06:52:42 ollama ollama[5962]: SIGABRT: abort
Feb 10 06:52:42 ollama ollama[5962]: PC=0x7ccc3749eb2c m=5 sigcode=18446744073709551610
Feb 10 06:52:42 ollama ollama[5962]: signal arrived during cgo execution
Feb 10 06:52:42 ollama ollama[5962]: goroutine 23 gp=0xc000504e00 m=5 mp=0xc000100008 [syscall]:
Feb 10 06:52:42 ollama ollama[5962]: runtime.cgocall(0x65331c7f2d00, 0xc0000490d8)
Feb 10 06:52:42 ollama ollama[5962]:         runtime/cgocall.go:167 +0x4b fp=0xc0000490b0 sp=0xc000049078 pc=0x65331b9a994b
Feb 10 06:52:42 ollama ollama[5962]: github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_reserve(0x7ccbdc79bfd0, 0x7ccb724e4e90)

...
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.680Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:39333/load\": EOF"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.681Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:39333/load\": dial tcp 
127.0.0.1:39333: connect: connection refused"
Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.681Z level=INFO source=sched.go:490 msg="Load failed" model=/root/.ollama/models/blobs/sha256-a3de86cd1c132c822487e
dedd47a324c50491393e6565cd14bafa40d0b8e686f error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details"
Feb 10 06:52:42 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:42 | 500 |  907.165692ms |       127.0.0.1 | POST     "/api/generate"
Feb 10 07:02:40 ollama ollama[5962]: [GIN] 2026/02/10 - 07:02:40 | 200 |      28.029µs |       127.0.0.1 | GET      "/api/version"
Feb 10 07:13:24 ollama systemd[1]: Stopping ollama.service - Ollama Service...

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.15.6

Originally created by @yunesj on GitHub (Feb 10, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14188 ### What is the issue? Ollama crashes RTX 3060 on cuda_v13 crashes v0.13.0 to v0.15.6. Deleting the cuda_v13, backend falls back to cuda_v12, and works, as it did in version <= 0.12.11. It seems similar to https://github.com/ollama/ollama/pull/12300. ### Relevant log output ```shell Feb 10 06:52:34 ollama ollama[5962]: time=2026-02-10T06:52:34.546Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:46567/load\": EOF" Feb 10 06:52:34 ollama ollama[5962]: time=2026-02-10T06:52:34.546Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:46567/load\": dial tcp 127.0.0.1:46567: connect: connection refused" Feb 10 06:52:34 ollama ollama[5962]: time=2026-02-10T06:52:34.546Z level=INFO source=sched.go:490 msg="Load failed" model=/root/.ollama/models/blobs/sha256-a3de86cd1c132c822487e dedd47a324c50491393e6565cd14bafa40d0b8e686f error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details" Feb 10 06:52:34 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:34 | 500 | 903.736937ms | 127.0.0.1 | POST "/api/generate" Feb 10 06:52:41 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:41 | 200 | 32.665µs | 127.0.0.1 | HEAD "/" Feb 10 06:52:41 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:41 | 200 | 129.807248ms | 127.0.0.1 | POST "/api/show" Feb 10 06:52:41 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:41 | 200 | 125.652266ms | 127.0.0.1 | POST "/api/show" Feb 10 06:52:41 ollama ollama[5962]: time=2026-02-10T06:52:41.952Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/lib/ollama/bin/ollama runner --ollama-en gine --port 36061" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.156Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsi ng \"max\": invalid syntax" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=server.go:247 msg="enabling flash attention" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=server.go:431 msg="startFeb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1411 msg="starting ollama engine" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:39333" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.260Z level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAt tention:Enabled KvSize:4096 KvCacheType: NumThreads:1 GPULayers:37[ID:GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 Us eMmap:false}" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.290Z level=INFO source=ggml.go:136 msg="" architecture=qwen3 file_type=Q4_K_M name="Qwen3 8B" description="" num_te nsors=399 num_key_values=29 Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CPU backend from /usr/local/lib/ollama/lib/ollama/libggml-cpu-haswell.so Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: found 1 CUDA devices: Feb 10 06:52:42 ollama ollama[5962]: Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6, VMM: yes, ID: GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/lib/ollama/cuda_v13/libggml-cuda.so Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.456Z 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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compile r=cgo(gcc) Feb 10 06:52:42 ollama ollama[5962]: free(): invalid pointer Feb 10 06:52:42 ollama ollama[5962]: SIGABRT: abort Feb 10 06:52:42 ollama ollama[5962]: PC=0x7ccc3749eb2c m=5 sigcode=18446744073709551610 Feb 10 06:52:42 ollama ollama[5962]: signal arrived during cgo execution Feb 10 06:52:42 ollama ollama[5962]: goroutine 23 gp=0xc000504e00 m=5 mp=0xc000100008 [syscall]: Feb 10 06:52:42 ollama ollama[5962]: runtime.cgocall(0x65331c7f2d00, 0xc0000490d8) Feb 10 06:52:42 ollama ollama[5962]: runtime/cgocall.go:167 +0x4b fp=0xc0000490b0 sp=0xc000049078 pc=0x65331b9a994b Feb 10 06:52:42 ollama ollama[5962]: github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_reserve(0x7ccbdc79bfd0, 0x7ccb724e4e90)ing runner" cmd="/usr/local/lib/ollama/bin/ollama runner --ollama-en gine --model /root/.ollama/models/blobs/sha256-a3de86cd1c132c822487ededd47a324c50491393e6565cd14bafa40d0b8e686f --port 39333" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=sched.go:463 msg="system memory" total="8.0 GiB" free="107.4 MiB" free_swap="512.0 MiB" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=sched.go:470 msg="gpu memory" id=GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 library=CUDA avail able="11.2 GiB" free="11.6 GiB" minimum="457.0 MiB" overhead="0 B" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.238Z level=INFO source=server.go:757 msg="loading model" "model layers"=37 requested=-1 Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1411 msg="starting ollama engine" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.249Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:39333" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.260Z level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAt tention:Enabled KvSize:4096 KvCacheType: NumThreads:1 GPULayers:37[ID:GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 Layers:37(0..36)] MultiUserCache:false ProjectorPath: MainGPU:0 Us eMmap:false}" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.290Z level=INFO source=ggml.go:136 msg="" architecture=qwen3 file_type=Q4_K_M name="Qwen3 8B" description="" num_te nsors=399 num_key_values=29 Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CPU backend from /usr/local/lib/ollama/lib/ollama/libggml-cpu-haswell.so Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Feb 10 06:52:42 ollama ollama[5962]: ggml_cuda_init: found 1 CUDA devices: Feb 10 06:52:42 ollama ollama[5962]: Device 0: NVIDIA GeForce RTX 3060, compute capability 8.6, VMM: yes, ID: GPU-60e3f5c9-f27e-4c35-502d-d4c9b9388f14 Feb 10 06:52:42 ollama ollama[5962]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/lib/ollama/cuda_v13/libggml-cuda.so Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.456Z 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 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compile r=cgo(gcc) Feb 10 06:52:42 ollama ollama[5962]: free(): invalid pointer Feb 10 06:52:42 ollama ollama[5962]: SIGABRT: abort Feb 10 06:52:42 ollama ollama[5962]: PC=0x7ccc3749eb2c m=5 sigcode=18446744073709551610 Feb 10 06:52:42 ollama ollama[5962]: signal arrived during cgo execution Feb 10 06:52:42 ollama ollama[5962]: goroutine 23 gp=0xc000504e00 m=5 mp=0xc000100008 [syscall]: Feb 10 06:52:42 ollama ollama[5962]: runtime.cgocall(0x65331c7f2d00, 0xc0000490d8) Feb 10 06:52:42 ollama ollama[5962]: runtime/cgocall.go:167 +0x4b fp=0xc0000490b0 sp=0xc000049078 pc=0x65331b9a994b Feb 10 06:52:42 ollama ollama[5962]: github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_reserve(0x7ccbdc79bfd0, 0x7ccb724e4e90) ... Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.680Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:39333/load\": EOF" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.681Z level=ERROR source=server.go:1205 msg="do load request" error="Post \"http://127.0.0.1:39333/load\": dial tcp 127.0.0.1:39333: connect: connection refused" Feb 10 06:52:42 ollama ollama[5962]: time=2026-02-10T06:52:42.681Z level=INFO source=sched.go:490 msg="Load failed" model=/root/.ollama/models/blobs/sha256-a3de86cd1c132c822487e dedd47a324c50491393e6565cd14bafa40d0b8e686f error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details" Feb 10 06:52:42 ollama ollama[5962]: [GIN] 2026/02/10 - 06:52:42 | 500 | 907.165692ms | 127.0.0.1 | POST "/api/generate" Feb 10 07:02:40 ollama ollama[5962]: [GIN] 2026/02/10 - 07:02:40 | 200 | 28.029µs | 127.0.0.1 | GET "/api/version" Feb 10 07:13:24 ollama systemd[1]: Stopping ollama.service - Ollama Service... ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.15.6
GiteaMirror added the needs more infobug labels 2026-04-12 22:07:20 -05:00
GiteaMirror commented 2026-04-12 22:07:22 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 10, 2026):

Set OLLAMA_DEBUG=2 and post the full log from start to the end of the model crashdump.

Note that you don't need to delete the cuda_v13 directory, set OLLAMA_LLIM_LIBRARY=cuda_v12 to force the runner to use v12.

<!-- gh-comment-id:3876877151 --> @rick-github commented on GitHub (Feb 10, 2026): Set `OLLAMA_DEBUG=2` and post the full log from start to the end of the model crashdump. Note that you don't need to delete the cuda_v13 directory, set `OLLAMA_LLIM_LIBRARY=cuda_v12` to force the runner to use v12.
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 needs more info
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#9247
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?