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 #8906] how to disable using cpu #5774

New Issue
Closed
opened 2026-04-12 17:06:32 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 17:06:32 -05:00
Owner
Copy Link

Originally created by @gyfprivate on GitHub (Feb 7, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8906

How can i just use gpu

Relevant log output

2025/02/07 09:49:54 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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_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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-02-07T09:49:54.790+08:00 level=INFO source=images.go:432 msg="total blobs: 7"
time=2025-02-07T09:49:54.791+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-02-07T09:49:54.791+08:00 level=INFO source=routes.go:1238 msg="Listening on [::]:11434 (version 0.5.7)"
time=2025-02-07T09:49:54.792+08:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx rocm_avx]"
time=2025-02-07T09:49:54.792+08:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs"
time=2025-02-07T09:49:54.792+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-02-07T09:49:54.792+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=4 efficiency=0 threads=8
time=2025-02-07T09:49:54.954+08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-34f0da31-c41c-fe70-128e-663782b879ee library=cuda variant=v12 compute=6.1 driver=12.8 name="NVIDIA GeForce GTX 1070 Ti" total="8.0 GiB" available="7.0 GiB"

Image

Image

OS
Windows

GPU
Nvidia

CPU
Intel

Ollama version
0.5.7

Originally created by @gyfprivate on GitHub (Feb 7, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8906 How can i just use gpu **Relevant log output** ``` 2025/02/07 09:49:54 routes.go:1187: INFO server config env="map[CUDA_VISIBLE_DEVICES:0 GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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_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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-02-07T09:49:54.790+08:00 level=INFO source=images.go:432 msg="total blobs: 7" time=2025-02-07T09:49:54.791+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-07T09:49:54.791+08:00 level=INFO source=routes.go:1238 msg="Listening on [::]:11434 (version 0.5.7)" time=2025-02-07T09:49:54.792+08:00 level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx rocm_avx]" time=2025-02-07T09:49:54.792+08:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2025-02-07T09:49:54.792+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-02-07T09:49:54.792+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=4 efficiency=0 threads=8 time=2025-02-07T09:49:54.954+08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-34f0da31-c41c-fe70-128e-663782b879ee library=cuda variant=v12 compute=6.1 driver=12.8 name="NVIDIA GeForce GTX 1070 Ti" total="8.0 GiB" available="7.0 GiB" ``` ![Image](https://github.com/user-attachments/assets/534c2fca-7436-41bf-a256-28aaf17efd7e) ![Image](https://github.com/user-attachments/assets/612e24b6-66b1-4e0a-a0f5-fc17b82e04bb) **OS** Windows GPU Nvidia CPU Intel Ollama version 0.5.7
GiteaMirror added the feature request label 2026-04-12 17:06:32 -05:00
GiteaMirror commented 2026-04-12 17:06:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 7, 2025):

Screenshot shows GPU being used. CPU is still used to give instructions and receive results.

<!-- gh-comment-id:2642301038 --> @rick-github commented on GitHub (Feb 7, 2025): Screenshot shows GPU being used. CPU is still used to give instructions and receive results.
GiteaMirror commented 2026-04-12 17:06:35 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Feb 8, 2025):

As @rick-github mentioned, this is working correctly. ollama ps shows the model offloaded to the GPU.

<!-- gh-comment-id:2644392292 --> @pdevine commented on GitHub (Feb 8, 2025): As @rick-github mentioned, this is working correctly. `ollama ps` shows the model offloaded to the GPU.
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 feature request
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#5774
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?