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 #1837] Ollama crashes quite often for Fedora 39 with NVIDIA T1200 Laptop GPU #63084

New Issue
Closed
opened 2026-05-03 11:43:24 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-03 11:43:24 -05:00
Owner
Copy Link

Originally created by @ilovepumpkin on GitHub (Jan 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/1837

Hello,

When I use ollama with NVIDIA T1200 Laptop GPU on Fedora 39, it crashes quite often regardless what models I am running. Is there any way to troubleshoot this issue?

Here is the output of nvidia-smi

+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 545.29.06              Driver Version: 545.29.06    CUDA Version: 12.3     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA T1200 Laptop GPU        Off | 00000000:01:00.0  On |                  N/A |
| N/A   44C    P8               6W /  60W |    303MiB /  4096MiB |      7%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|    0   N/A  N/A      3280      G   /usr/libexec/Xorg                           115MiB |
|    0   N/A  N/A      4776    C+G   ...seed-version=20240105-201042.648000      177MiB |
+---------------------------------------------------------------------------------------+
Originally created by @ilovepumpkin on GitHub (Jan 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/1837 Hello, When I use ollama with NVIDIA T1200 Laptop GPU on Fedora 39, it crashes quite often regardless what models I am running. Is there any way to troubleshoot this issue? Here is the output of `nvidia-smi` ``` +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 545.29.06 Driver Version: 545.29.06 CUDA Version: 12.3 | |-----------------------------------------+----------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA T1200 Laptop GPU Off | 00000000:01:00.0 On | N/A | | N/A 44C P8 6W / 60W | 303MiB / 4096MiB | 7% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+ +---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | 0 N/A N/A 3280 G /usr/libexec/Xorg 115MiB | | 0 N/A N/A 4776 C+G ...seed-version=20240105-201042.648000 177MiB | +---------------------------------------------------------------------------------------+ ```
GiteaMirror commented 2026-05-03 11:43:26 -05:00
Author
Owner
Copy Link

@ilovepumpkin commented on GitHub (Jan 7, 2024):

I got the following "out of memory" error when using ollama v0.1.18.

CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml-cuda.cu:9132: out of memory
current device: 0
GGML_ASSERT: /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml-cuda.cu:9132: !"CUDA error"

However, it seems working well after I switching to v0.1.17.

<!-- gh-comment-id:1880025393 --> @ilovepumpkin commented on GitHub (Jan 7, 2024): I got the following "out of memory" error when using ollama v0.1.18. ``` CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml-cuda.cu:9132: out of memory current device: 0 GGML_ASSERT: /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml-cuda.cu:9132: !"CUDA error" ``` However, it seems working well after I switching to v0.1.17.
GiteaMirror commented 2026-05-03 11:43:27 -05:00
Author
Owner
Copy Link

@ilovepumpkin commented on GitHub (Jan 7, 2024):

Well, after using it for a while, I am still getting the error Error: llama runner exited, you may not have enough available memory to run this model

<!-- gh-comment-id:1880039983 --> @ilovepumpkin commented on GitHub (Jan 7, 2024): Well, after using it for a while, I am still getting the error `Error: llama runner exited, you may not have enough available memory to run this model `
GiteaMirror commented 2026-05-03 11:43:28 -05:00
Author
Owner
Copy Link

@ilovepumpkin commented on GitHub (Jan 8, 2024):

I keep getting "out of memory" error when using v0.1.17, even in v0.1.14. Especially when I try to integrate ollama with anythingLLM ( https://github.com/Mintplex-Labs/anything-llm ), it crashes quite often.

2024/01/08 15:18:14 llama.go:506: llama runner started in 1.401141 seconds

CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5924: out of memory
current device: 0
2024/01/08 15:18:32 llama.go:449: 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5924: out of memory
current device: 0
2024/01/08 15:18:32 llama.go:523: llama runner stopped successfully
[GIN] 2024/01/08 - 15:18:32 | 200 | 19.310051007s |       127.0.0.1 | POST     "/api/generate"
^C2024/01/08 15:19:16 llama.go:523: llama runner stopped successfully
<!-- gh-comment-id:1880491510 --> @ilovepumpkin commented on GitHub (Jan 8, 2024): I keep getting "out of memory" error when using v0.1.17, even in v0.1.14. Especially when I try to integrate ollama with anythingLLM ( https://github.com/Mintplex-Labs/anything-llm ), it crashes quite often. ``` 2024/01/08 15:18:14 llama.go:506: llama runner started in 1.401141 seconds CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5924: out of memory current device: 0 2024/01/08 15:18:32 llama.go:449: 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5924: out of memory current device: 0 2024/01/08 15:18:32 llama.go:523: llama runner stopped successfully [GIN] 2024/01/08 - 15:18:32 | 200 | 19.310051007s | 127.0.0.1 | POST "/api/generate" ^C2024/01/08 15:19:16 llama.go:523: llama runner stopped successfully ```
GiteaMirror commented 2026-05-03 11:43:28 -05:00
Author
Owner
Copy Link

@ilovepumpkin commented on GitHub (Jan 8, 2024):

It looks like that the crash is related to how ollama is used - when I use it in VSCode Continue extention, it is stable. but when it being used in AnytingLLM, it crashes very quickly. Does this mean I should report a bug to AnythingLLM?

<!-- gh-comment-id:1880659679 --> @ilovepumpkin commented on GitHub (Jan 8, 2024): It looks like that the crash is related to how ollama is used - when I use it in VSCode Continue extention, it is stable. but when it being used in AnytingLLM, it crashes very quickly. Does this mean I should report a bug to AnythingLLM?
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
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#63084
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?