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 #9124] can i use nvidia tesla k80 gpu run a model? #83619

New Issue
Closed
opened 2026-05-09 18:44:28 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-09 18:44:28 -05:00
Owner
Copy Link

Originally created by @mayunqing1230 on GitHub (Feb 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9124

What is the issue?

my server have 4 nvidia tesla k80 24gb gpu and 256gb mem, can i only use gpu run a model? ollama can't find my gpu and use cpu

Relevant log output

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.11

Originally created by @mayunqing1230 on GitHub (Feb 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9124 ### What is the issue? my server have 4 nvidia tesla k80 24gb gpu and 256gb mem, can i only use gpu run a model? ollama can't find my gpu and use cpu ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.11
GiteaMirror added the bug label 2026-05-09 18:44:28 -05:00
GiteaMirror commented 2026-05-09 18:44:29 -05:00
Author
Owner
Copy Link

@LeisureLinux commented on GitHub (Feb 15, 2025):

if on Linux, normally you would have nvidia-smi command running and tell your gpu info. like below:

Image

If you are on Debian/Ubuntu, suggest you install the non-free-firmware from OS repo. not Nvidia version.

<!-- gh-comment-id:2660823798 --> @LeisureLinux commented on GitHub (Feb 15, 2025): if on Linux, normally you would have nvidia-smi command running and tell your gpu info. like below: <img width="689" alt="Image" src="https://github.com/user-attachments/assets/faf7f528-fadc-4cc7-9664-6fa9a1ddc25d" /> If you are on Debian/Ubuntu, suggest you install the non-free-firmware from OS repo. not Nvidia version.
GiteaMirror commented 2026-05-09 18:44:30 -05:00
Author
Owner
Copy Link

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

Server logs will help in debugging.

<!-- gh-comment-id:2660887947 --> @rick-github commented on GitHub (Feb 15, 2025): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) will help in debugging.
GiteaMirror commented 2026-05-09 18:44:30 -05:00
Author
Owner
Copy Link

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

Actually, K80 has a compute capacity of 3.7 and is not supported, ollama supports CC 5.0 and above.

<!-- gh-comment-id:2660893999 --> @rick-github commented on GitHub (Feb 15, 2025): Actually, K80 has a compute capacity of [3.7](https://developer.nvidia.com/cuda-gpus) and is not supported, ollama supports CC [5.0 and above](https://github.com/ollama/ollama/blob/main/docs/gpu.md#nvidia).
GiteaMirror commented 2026-05-09 18:44:31 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Feb 16, 2025):

@mayunqing1230 unfortunately those cards are really old now and are probably not going to be very performant. I'm going to go ahead and close the issue.

<!-- gh-comment-id:2661196309 --> @pdevine commented on GitHub (Feb 16, 2025): @mayunqing1230 unfortunately those cards are really old now and are probably not going to be very performant. I'm going to go ahead and close the issue.
GiteaMirror commented 2026-05-09 18:44:31 -05:00
Author
Owner
Copy Link

@shalomfriss commented on GitHub (Oct 18, 2025):

There is a repo out there that helps. Any way to get this integrated? It's only 2 lines different
https://github.com/austinksmith/ollama37

<!-- gh-comment-id:3418334595 --> @shalomfriss commented on GitHub (Oct 18, 2025): There is a repo out there that helps. Any way to get this integrated? It's only 2 lines different https://github.com/austinksmith/ollama37
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#83619
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?