github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11426] Error:"nil pointer dereference" panic when running my fine-tune Gemma3 #7543

New Issue
Open
opened 2026-04-12 19:38:36 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 19:38:36 -05:00
Owner
Copy Link

Originally created by @CheeseSilly on GitHub (Jul 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11426

What is the issue?

When i ran my fine-tune Gemma3-4b on my laptop,it just caused some errors.

[signal 0xc0000005 code=0x0 addr=0x0 pc=0x7ff6b3b759d9]

goroutine 66 [running]:
github.com/ollama/ollama/ml/nn.(*Conv2D).Forward(...)
        C:/a/ollama/ollama/ml/nn/convolution.go:10
github.com/ollama/ollama/model/models/gemma3.(*VisionModel).Forward(0xc0000a9a40, {0x7ff6b4a6bc70, 0xc001d4ba00}, {0x7ff6b4a78dc0?, 0xc001d52000?})
        C:/a/ollama/ollama/model/models/gemma3/model_vision.go:91 +0x99
github.com/ollama/ollama/model/models/gemma3.(*Model).EncodeMultimodal(0xc001c48000, {0x7ff6b4a6bc70, 0xc001d4ba00}, {0xc0028c6000, 0x400436,

And i checked the log, it indicated a memory issue.

fatal error: runtime: cannot allocate memory

But i can run it on llama factory on the cloud server,no errors.

So i tried to pull the original version, Gemma-3-4b-it from modelscope.

And it just ran normally.

i dont know how to deal with it,and it seems to be unrelative to my memory limitations or fine-tune model itself.

RAM: 32GB
GPU: RTX4060
CPU: Intel i9-13900H

Relevant log output

time=2025-07-15T13:11:45.848+08:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:http://127.0.0.1:20112 HTTP_PROXY:http://127.0.0.1:20112 NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\\ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-07-15T13:11:45.985+08:00 level=INFO source=images.go:476 msg="total blobs: 27"
time=2025-07-15T13:11:45.998+08:00 level=INFO source=images.go:483 msg="total unused blobs removed: 13"
time=2025-07-15T13:11:45.998+08:00 level=INFO source=routes.go:1288 msg="Listening on 127.0.0.1:11434 (version 0.9.6)"
time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=14 efficiency=8 threads=20
time=2025-07-15T13:11:46.215+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d4e272d1-0429-88a0-11bb-0cafe04988d8 library=cuda variant=v12 compute=8.9 driver=12.9 name="NVIDIA GeForce RTX 4060 Laptop GPU" total="8.0 GiB" available="6.9 GiB"
[GIN] 2025/07/15 - 13:11:46 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/07/15 - 13:11:46 | 200 |      1.0343ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/07/15 - 13:12:03 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/07/15 - 13:12:06 | 201 |       2.151ms |       127.0.0.1 | POST     "/api/blobs/sha256:d7d146e2236a04ae124df275c97e2db40574c63cc0726c5311db515e77107cf7"
[GIN] 2025/07/15 - 13:12:06 | 201 |      4.7251ms |       127.0.0.1 | POST     "/api/blobs/sha256:db561986582658fc37d01f39a800c1c684efd9a52df5dec771c3fc907fbb8dd2"
[GIN] 2025/07/15 - 13:12:06 | 201 |      4.7251ms |       127.0.0.1 | POST     "/api/blobs/sha256:e6ddeb92989c50407f65674692eb10734aa13d2ef73c323ce738b22aedce7bac"
[GIN] 2025/07/15 - 13:12:06 | 201 |      4.1706ms |       127.0.0.1 | POST     "/api/blobs/sha256:cae167ad6e91668fa74073f6d28125a675c96bdded41e1896cc61cf7d4612260"
[GIN] 2025/07/15 - 13:12:06 | 201 |      4.6916ms |       127.0.0.1 | POST     "/api/blobs/sha256:3ffd5f11778dc73e2b69b3c00535e4121e1badf7018136263cd17b5b34fbaa53"
[GIN] 2025/07/15 - 13:12:06 | 201 |      3.6535ms |       127.0.0.1 | POST     "/api/blobs/sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946"
[GIN] 2025/07/15 - 13:12:06 | 201 |      3.6535ms |       127.0.0.1 | POST     "/api/blobs/sha256:45a857d8a2495d0be30a5d2d6de03278195eb028b6e0b8efc248bfa697d65f05"
[GIN] 2025/07/15 - 13:12:06 | 201 |     16.5275ms |       127.0.0.1 | POST     "/api/blobs/sha256:a1fb770bb412598d213bf23b1a4ad7219720ced69c228f19e852176735fb8ca2"
[GIN] 2025/07/15 - 13:12:06 | 201 |    100.3148ms |       127.0.0.1 | POST     "/api/blobs/sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795"
[GIN] 2025/07/15 - 13:12:17 | 201 |   10.1696138s |       127.0.0.1 | POST     "/api/blobs/sha256:d7f6d83d59f25643e75609b5fef1cde803c01ddcc8bd9f7427ac97934a9079db"
[GIN] 2025/07/15 - 13:12:19 | 201 |   13.0647825s |       127.0.0.1 | POST     "/api/blobs/sha256:c9aa71ee0597b25a62121bb794a0ce46b245a059e94e74ad510ea9be41318ecf"
fatal error: runtime: cannot allocate memory

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.9.6

Originally created by @CheeseSilly on GitHub (Jul 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11426 ### What is the issue? When i ran my fine-tune Gemma3-4b on my laptop,it just caused some errors. ``` [signal 0xc0000005 code=0x0 addr=0x0 pc=0x7ff6b3b759d9] goroutine 66 [running]: github.com/ollama/ollama/ml/nn.(*Conv2D).Forward(...) C:/a/ollama/ollama/ml/nn/convolution.go:10 github.com/ollama/ollama/model/models/gemma3.(*VisionModel).Forward(0xc0000a9a40, {0x7ff6b4a6bc70, 0xc001d4ba00}, {0x7ff6b4a78dc0?, 0xc001d52000?}) C:/a/ollama/ollama/model/models/gemma3/model_vision.go:91 +0x99 github.com/ollama/ollama/model/models/gemma3.(*Model).EncodeMultimodal(0xc001c48000, {0x7ff6b4a6bc70, 0xc001d4ba00}, {0xc0028c6000, 0x400436, ``` And i checked the log, it indicated a memory issue. ``` fatal error: runtime: cannot allocate memory ``` But i can run it on llama factory on the cloud server,no errors. So i tried to pull the original version, Gemma-3-4b-it from modelscope. And it just ran normally. i dont know how to deal with it,and it seems to be unrelative to my memory limitations or fine-tune model itself. RAM: 32GB GPU: RTX4060 CPU: Intel i9-13900H ### Relevant log output ```shell time=2025-07-15T13:11:45.848+08:00 level=INFO source=routes.go:1235 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY:http://127.0.0.1:20112 HTTP_PROXY:http://127.0.0.1:20112 NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\\ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-07-15T13:11:45.985+08:00 level=INFO source=images.go:476 msg="total blobs: 27" time=2025-07-15T13:11:45.998+08:00 level=INFO source=images.go:483 msg="total unused blobs removed: 13" time=2025-07-15T13:11:45.998+08:00 level=INFO source=routes.go:1288 msg="Listening on 127.0.0.1:11434 (version 0.9.6)" time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-07-15T13:11:45.998+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=14 efficiency=8 threads=20 time=2025-07-15T13:11:46.215+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d4e272d1-0429-88a0-11bb-0cafe04988d8 library=cuda variant=v12 compute=8.9 driver=12.9 name="NVIDIA GeForce RTX 4060 Laptop GPU" total="8.0 GiB" available="6.9 GiB" [GIN] 2025/07/15 - 13:11:46 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/07/15 - 13:11:46 | 200 | 1.0343ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/07/15 - 13:12:03 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/07/15 - 13:12:06 | 201 | 2.151ms | 127.0.0.1 | POST "/api/blobs/sha256:d7d146e2236a04ae124df275c97e2db40574c63cc0726c5311db515e77107cf7" [GIN] 2025/07/15 - 13:12:06 | 201 | 4.7251ms | 127.0.0.1 | POST "/api/blobs/sha256:db561986582658fc37d01f39a800c1c684efd9a52df5dec771c3fc907fbb8dd2" [GIN] 2025/07/15 - 13:12:06 | 201 | 4.7251ms | 127.0.0.1 | POST "/api/blobs/sha256:e6ddeb92989c50407f65674692eb10734aa13d2ef73c323ce738b22aedce7bac" [GIN] 2025/07/15 - 13:12:06 | 201 | 4.1706ms | 127.0.0.1 | POST "/api/blobs/sha256:cae167ad6e91668fa74073f6d28125a675c96bdded41e1896cc61cf7d4612260" [GIN] 2025/07/15 - 13:12:06 | 201 | 4.6916ms | 127.0.0.1 | POST "/api/blobs/sha256:3ffd5f11778dc73e2b69b3c00535e4121e1badf7018136263cd17b5b34fbaa53" [GIN] 2025/07/15 - 13:12:06 | 201 | 3.6535ms | 127.0.0.1 | POST "/api/blobs/sha256:50b2f405ba56a26d4913fd772089992252d7f942123cc0a034d96424221ba946" [GIN] 2025/07/15 - 13:12:06 | 201 | 3.6535ms | 127.0.0.1 | POST "/api/blobs/sha256:45a857d8a2495d0be30a5d2d6de03278195eb028b6e0b8efc248bfa697d65f05" [GIN] 2025/07/15 - 13:12:06 | 201 | 16.5275ms | 127.0.0.1 | POST "/api/blobs/sha256:a1fb770bb412598d213bf23b1a4ad7219720ced69c228f19e852176735fb8ca2" [GIN] 2025/07/15 - 13:12:06 | 201 | 100.3148ms | 127.0.0.1 | POST "/api/blobs/sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795" [GIN] 2025/07/15 - 13:12:17 | 201 | 10.1696138s | 127.0.0.1 | POST "/api/blobs/sha256:d7f6d83d59f25643e75609b5fef1cde803c01ddcc8bd9f7427ac97934a9079db" [GIN] 2025/07/15 - 13:12:19 | 201 | 13.0647825s | 127.0.0.1 | POST "/api/blobs/sha256:c9aa71ee0597b25a62121bb794a0ce46b245a059e94e74ad510ea9be41318ecf" fatal error: runtime: cannot allocate memory ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.9.6
GiteaMirror added the bug label 2026-04-12 19:38:36 -05:00
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#7543
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?