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 #5650] Can't install the latest ollama version to run gemma2 #65561

New Issue
Closed
opened 2026-05-03 21:41:56 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-03 21:41:56 -05:00
Owner
Copy Link

Originally created by @pizdoponi on GitHub (Jul 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5650

What is the issue?

I have installed the latest stable version (v0.2.1) from the releases page. However, after checking the version, it makes a distinction between ollama version and client version.

❯ ollama --version
ollama version is 0.1.44
Warning: client version is 0.2.1

Before that I had installed ollama via homebrew, but saw a few issues relating to the problem of installing ollama through homebrew, which is why I removed the homebrew version.

The problem is when I try to run gemma 2 model:
❯ ollama run gemma2
Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'gemma2'

As per #5369 the problem is that I should be running ollama version >= 0.1.47. Did I do something wrong during the installation? After deleting the homebrew version I checked with which ollama do ensure there wasn't any binary left. I now run ollama via the Ollama.app.

Note: Other models like llama3 and phi3 work as expected.

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.44

Originally created by @pizdoponi on GitHub (Jul 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5650 ### What is the issue? I have installed the latest stable version (v0.2.1) from [the releases page](https://github.com/ollama/ollama/releases). However, after checking the version, it makes a distinction between ollama version and client version. ❯ ollama --version ollama version is 0.1.44 Warning: client version is 0.2.1 Before that I had installed ollama via homebrew, but saw a few issues relating to the problem of installing ollama through homebrew, which is why I removed the homebrew version. The problem is when I try to run gemma 2 model: ❯ ollama run gemma2 Error: llama runner process has terminated: signal: abort trap error:error loading model architecture: unknown model architecture: 'gemma2' As per #5369 the problem is that I should be running ollama version >= 0.1.47. Did I do something wrong during the installation? After deleting the homebrew version I checked with `which ollama` do ensure there wasn't any binary left. I now run ollama via the Ollama.app. Note: Other models like llama3 and phi3 work as expected. ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.44
GiteaMirror added the bug label 2026-05-03 21:41:56 -05:00
GiteaMirror commented 2026-05-03 21:42:00 -05:00
Author
Owner
Copy Link

@pizdoponi commented on GitHub (Jul 12, 2024):

If anyone else has the same issue, cold rebooting seemed to solve the issue for me. Maybe it was something else, but now it seems to work, as (both) ollama version is 0.2.1

I am now able to run gemma2, so I confirm if was the version problem. If you downloaded ollama through homebrew in the past, make sure to delete everything so the versions don't get mixed up (like it seems it did in my case).

<!-- gh-comment-id:2225438387 --> @pizdoponi commented on GitHub (Jul 12, 2024): If anyone else has the same issue, cold rebooting seemed to solve the issue for me. Maybe it was something else, but now it seems to work, as (both) ollama version is 0.2.1 I am now able to run gemma2, so I confirm if was the version problem. If you downloaded ollama through homebrew in the past, make sure to delete everything so the versions don't get mixed up (like it seems it did in my case).
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#65561
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?