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 #3771] Ollama is not using GPU to run model on Windows 11 #48839

New Issue
Closed
opened 2026-04-28 09:42:30 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-28 09:42:30 -05:00
Owner
Copy Link

Originally created by @maxithub on GitHub (Apr 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3771

What is the issue?

version: 0.1.31
gpu: nvidia qradro p2000 (5GB GPU memory)
os: win 11
cuda:
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corporation
Built on Fri_Nov__3_17:51:05_Pacific_Daylight_Time_2023
Cuda compilation tools, release 12.3, V12.3.103
Build cuda_12.3.r12.3/compiler.33492891_0
Command: ollama run tinydolphin
Screenshot 2024-04-20 121734
the 2nd column is CPU (20%), the 3rd one is GPU (0%)

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.31

Originally created by @maxithub on GitHub (Apr 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3771 ### What is the issue? **version:** 0.1.31 **gpu:** nvidia qradro p2000 (5GB GPU memory) **os:** win 11 **cuda:** nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2023 NVIDIA Corporation Built on Fri_Nov__3_17:51:05_Pacific_Daylight_Time_2023 Cuda compilation tools, release 12.3, V12.3.103 Build cuda_12.3.r12.3/compiler.33492891_0 **Command:** ollama run tinydolphin ![Screenshot 2024-04-20 121734](https://github.com/ollama/ollama/assets/11460496/4e0853e7-14c9-4138-a031-003553dd1c7f) the 2nd column is CPU (20%), the 3rd one is GPU (0%) ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.31
GiteaMirror added the bug label 2026-04-28 09:42:30 -05:00
GiteaMirror commented 2026-04-28 09:42:34 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Apr 20, 2024):

Hi @maxithub can you update to version 0.1.32 of Ollama ans tell us if you reproduce the same issue?

<!-- gh-comment-id:2067603320 --> @igorschlum commented on GitHub (Apr 20, 2024): Hi @maxithub can you update to version 0.1.32 of Ollama ans tell us if you reproduce the same issue?
GiteaMirror commented 2026-04-28 09:42:35 -05:00
Author
Owner
Copy Link

@maxithub commented on GitHub (Apr 21, 2024):

@igorschlum thank you very much for the swift response. I just upgraded to 0.1.32, and noticed there is a new process named ollama_llama_server created to run the model. Unfortunately, the problem still persists.
image

I just got this in the server.log file.
server.log

<!-- gh-comment-id:2067854369 --> @maxithub commented on GitHub (Apr 21, 2024): @igorschlum thank you very much for the swift response. I just upgraded to 0.1.32, and noticed there is a new process named ollama_llama_server created to run the model. Unfortunately, the problem still persists. ![image](https://github.com/ollama/ollama/assets/11460496/7e98af68-7e9e-412e-8a4a-7bb5c8282145) I just got this in the server.log file. [server.log](https://github.com/ollama/ollama/files/15050997/server.log)
GiteaMirror commented 2026-04-28 09:42:35 -05:00
Author
Owner
Copy Link

@TuziwochatGPT commented on GitHub (Apr 21, 2024):

我也出现了同样的问题，它只占用我的cup算力，显卡无法使用

<!-- gh-comment-id:2067917152 --> @TuziwochatGPT commented on GitHub (Apr 21, 2024): 我也出现了同样的问题，它只占用我的cup算力，显卡无法使用
GiteaMirror commented 2026-04-28 09:42:36 -05:00
Author
Owner
Copy Link

@maxithub commented on GitHub (Apr 21, 2024):

Ohh, finally got it working now after install the latest CUDA version cuda_12.4.1_551.78_windows.exe
image

Really love the simplicity offered by Ollama! One command and things just work! Thank you so much for the brilliant work!

<!-- gh-comment-id:2067969404 --> @maxithub commented on GitHub (Apr 21, 2024): Ohh, finally got it working now after install the latest CUDA version [cuda_12.4.1_551.78_windows.exe](https://developer.download.nvidia.com/compute/cuda/12.4.1/local_installers/cuda_12.4.1_551.78_windows.exe) ![image](https://github.com/ollama/ollama/assets/11460496/3166158c-c886-41c9-8f5d-0376c50ffe08) Really love the simplicity offered by Ollama! One command and things just work! Thank you so much for the brilliant work!
GiteaMirror commented 2026-04-28 09:42:36 -05:00
Author
Owner
Copy Link

@TuziwochatGPT commented on GitHub (Apr 21, 2024):

谢谢，已通知富健，他会及时查看。

<!-- gh-comment-id:2067969640 --> @TuziwochatGPT commented on GitHub (Apr 21, 2024): 谢谢，已通知富健，他会及时查看。
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#48839
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?