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 #5627] unknown model architecture: 'gemma2' #50021

New Issue
Closed
opened 2026-04-28 13:51:46 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 13:51:46 -05:00
Owner
Copy Link

Originally created by @mouse33333 on GitHub (Jul 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5627

What is the issue?

I'm trying to run models on my internal Intel GPU.

Here's the software env:

  1. activate a virtual env in Anaconda
  2. already installed ipex-llm[cpp], ipex-llm[xpu]
  3. start the Ollama serve
  4. start gemma2 model

Then the log said: unknown model architecture: 'gemma2'

Here's the sreenshot of the log:

screenshot-20240711-154648

OS

Windows, Docker

GPU

Intel

CPU

Intel

Ollama version

0.2.1

Originally created by @mouse33333 on GitHub (Jul 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5627 ### What is the issue? I'm trying to run models on my internal Intel GPU. Here's the software env: 1. activate a virtual env in Anaconda 2. already installed ipex-llm[cpp], ipex-llm[xpu] 3. start the Ollama serve 4. start gemma2 model Then the log said: unknown model architecture: 'gemma2' Here's the sreenshot of the log: ![screenshot-20240711-154648](https://github.com/ollama/ollama/assets/4304174/b7e59f45-c7bc-4e62-86dc-93f1083b8b55) ### OS Windows, Docker ### GPU Intel ### CPU Intel ### Ollama version 0.2.1
GiteaMirror added the bug label 2026-04-28 13:51:46 -05:00
GiteaMirror commented 2026-04-28 13:51:56 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jul 11, 2024):

Hi there, thanks for the issue. Are you sure you are on 0.2.1 in the Docker container? Gemma 2 has been supported for the last few releases. Would it be possible to try re-pulling the Docker image docker pull ollama/ollama? or checking ollama -v from within it? Let me know if that doesn't work

<!-- gh-comment-id:2222275345 --> @jmorganca commented on GitHub (Jul 11, 2024): Hi there, thanks for the issue. Are you sure you are on 0.2.1 in the Docker container? Gemma 2 has been supported for the last few releases. Would it be possible to try re-pulling the Docker image `docker pull ollama/ollama`? or checking `ollama -v` from within it? Let me know if that doesn't work
GiteaMirror commented 2026-04-28 13:51:57 -05:00
Author
Owner
Copy Link

@mouse33333 commented on GitHub (Jul 11, 2024):

Appology for my mistake. I just run Ollama on windows. The client version is 0.2.1

The Gemma2 works fine when running on CPU. However if I use Ollama serve mode and try to run the model on my iGPU (which is INTEL), it went wrong.

<!-- gh-comment-id:2222289441 --> @mouse33333 commented on GitHub (Jul 11, 2024): Appology for my mistake. I just run Ollama on windows. The client version is 0.2.1 The Gemma2 works fine when running on CPU. However if I use Ollama serve mode and try to run the model on my iGPU (which is INTEL), it went wrong.
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#50021
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?