github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12220] Intel Core Ultra 5 235 GPU/NPU not found #54644

New Issue
Closed
opened 2026-04-29 06:45:18 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 06:45:18 -05:00
Owner
Copy Link

Originally created by @morpher412 on GitHub (Sep 8, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12220

What is the issue?

I am using Proxmox VE using a privileged LXC , and that the Intel Core Ultra 5 235 GPU/NPU is not being detected. I am unsure if this is a bug or undeveloped feature, but my understanding was that OpenVino would support these integrated pieces of hardware.

Relevant log output

root@ai-server:~# journalctl -u ollama.service
Sep 08 22:39:34 ai-server systemd[1]: Started ollama.service - Ollama Service.
Sep 08 22:39:34 ai-server ollama[6592]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key.
Sep 08 22:39:34 ai-server ollama[6592]: Your new public key is:
Sep 08 22:39:34 ai-server ollama[6592]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIEgVUFVj7f5PThQpxMWjObd7tvaPR9HXXQHlnxLxGLbM
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.934Z level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: H>
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.935Z level=INFO source=images.go:477 msg="total blobs: 0"
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.935Z level=INFO source=images.go:484 msg="total unused blobs removed: 0"
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.936Z level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.10)"
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.937Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.941Z level=INFO source=gpu.go:388 msg="no compatible GPUs were discovered"
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.941Z level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="16.0 G>
Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.941Z level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB"
Sep 08 22:41:44 ai-server systemd[1]: Stopping ollama.service - Ollama Service...
Sep 08 22:41:44 ai-server systemd[1]: ollama.service: Deactivated successfully.
Sep 08 22:41:44 ai-server systemd[1]: Stopped ollama.service - Ollama Service.
-- Boot 8f3ab5b18b0e4906be202629cb67d4ab --
Sep 08 22:41:48 ai-server systemd[1]: Started ollama.service - Ollama Service.
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.460Z level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HS>
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.461Z level=INFO source=images.go:477 msg="total blobs: 0"
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.461Z level=INFO source=images.go:484 msg="total unused blobs removed: 0"
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.462Z level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.10)"
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.462Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.465Z level=INFO source=gpu.go:388 msg="no compatible GPUs were discovered"
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.465Z level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="16.0 Gi>
Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.465Z level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB"
Sep 08 22:42:39 ai-server systemd[1]: Stopping ollama.service - Ollama Service...
Sep 08 22:42:39 ai-server systemd[1]: ollama.service: Deactivated successfully.
Sep 08 22:42:39 ai-server systemd[1]: Stopped ollama.service - Ollama Service.
Sep 08 22:42:39 ai-server systemd[1]: Started ollama.service - Ollama Service.

OS

Linux

GPU

Intel

CPU

Intel

Ollama version

No response

Originally created by @morpher412 on GitHub (Sep 8, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12220 ### What is the issue? I am using Proxmox VE using a privileged LXC , and that the Intel Core Ultra 5 235 GPU/NPU is not being detected. I am unsure if this is a bug or undeveloped feature, but my understanding was that OpenVino would support these integrated pieces of hardware. ### Relevant log output ```shell root@ai-server:~# journalctl -u ollama.service Sep 08 22:39:34 ai-server systemd[1]: Started ollama.service - Ollama Service. Sep 08 22:39:34 ai-server ollama[6592]: Couldn't find '/usr/share/ollama/.ollama/id_ed25519'. Generating new private key. Sep 08 22:39:34 ai-server ollama[6592]: Your new public key is: Sep 08 22:39:34 ai-server ollama[6592]: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIEgVUFVj7f5PThQpxMWjObd7tvaPR9HXXQHlnxLxGLbM Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.934Z level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: H> Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.935Z level=INFO source=images.go:477 msg="total blobs: 0" Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.935Z level=INFO source=images.go:484 msg="total unused blobs removed: 0" Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.936Z level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.10)" Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.937Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.941Z level=INFO source=gpu.go:388 msg="no compatible GPUs were discovered" Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.941Z level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="16.0 G> Sep 08 22:39:34 ai-server ollama[6592]: time=2025-09-08T22:39:34.941Z level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB" Sep 08 22:41:44 ai-server systemd[1]: Stopping ollama.service - Ollama Service... Sep 08 22:41:44 ai-server systemd[1]: ollama.service: Deactivated successfully. Sep 08 22:41:44 ai-server systemd[1]: Stopped ollama.service - Ollama Service. -- Boot 8f3ab5b18b0e4906be202629cb67d4ab -- Sep 08 22:41:48 ai-server systemd[1]: Started ollama.service - Ollama Service. Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.460Z level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HS> Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.461Z level=INFO source=images.go:477 msg="total blobs: 0" Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.461Z level=INFO source=images.go:484 msg="total unused blobs removed: 0" Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.462Z level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.10)" Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.462Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.465Z level=INFO source=gpu.go:388 msg="no compatible GPUs were discovered" Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.465Z level=INFO source=types.go:131 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="16.0 Gi> Sep 08 22:41:48 ai-server ollama[272]: time=2025-09-08T22:41:48.465Z level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB" Sep 08 22:42:39 ai-server systemd[1]: Stopping ollama.service - Ollama Service... Sep 08 22:42:39 ai-server systemd[1]: ollama.service: Deactivated successfully. Sep 08 22:42:39 ai-server systemd[1]: Stopped ollama.service - Ollama Service. Sep 08 22:42:39 ai-server systemd[1]: Started ollama.service - Ollama Service. ``` ### OS Linux ### GPU Intel ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 06:45:18 -05:00
GiteaMirror commented 2026-04-29 06:45:26 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 8, 2025):

Ollama doesn't use OpenVino.

<!-- gh-comment-id:3268364560 --> @rick-github commented on GitHub (Sep 8, 2025): Ollama doesn't use OpenVino.
GiteaMirror commented 2026-04-29 06:45:28 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Sep 9, 2025):

Unfortunately it's not supported, but it is something we've been talking about supporting.

<!-- gh-comment-id:3271536595 --> @pdevine commented on GitHub (Sep 9, 2025): Unfortunately it's not supported, but it is something we've been talking about supporting.
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#54644
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?