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 #9682] Ollama 0.6.0: unknown model architecture: 'gemma3' #32078

New Issue
Closed
opened 2026-04-22 12:59:22 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 12:59:22 -05:00
Owner
Copy Link

Originally created by @chigkim on GitHub (Mar 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9682

Originally assigned to: @pdevine on GitHub.

What is the issue?

Are more quants for gemma3 coming to Ollama library? There seem to be only q4_K_M and fp16.
I tried to quantize to q8_0, and I got this error.

modelfile:
FROM gemma3:27b-it-fp16

% ollama create gemma3:27-it-q8_0 --quantize q8_0 -f gemma3.modelfile

Relevant log output

gathering model components 
quantizing F16 model to Q8_0 
Error: llama_model_quantize: 1

Log:
llama_model_quantize: failed to quantize: unknown model architecture: 'gemma3'

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.6.0

Originally created by @chigkim on GitHub (Mar 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9682 Originally assigned to: @pdevine on GitHub. ### What is the issue? Are more quants for gemma3 coming to Ollama library? There seem to be only q4_K_M and fp16. I tried to quantize to q8_0, and I got this error. modelfile: FROM gemma3:27b-it-fp16 % ollama create gemma3:27-it-q8_0 --quantize q8_0 -f gemma3.modelfile ### Relevant log output ```shell gathering model components quantizing F16 model to Q8_0 Error: llama_model_quantize: 1 Log: llama_model_quantize: failed to quantize: unknown model architecture: 'gemma3' ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.6.0
GiteaMirror added the bug label 2026-04-22 12:59:22 -05:00
GiteaMirror commented 2026-04-22 12:59:23 -05:00
Author
Owner
Copy Link

@Hioness commented on GitHub (Mar 12, 2025):

I've had the same issue with the 1b version.

> ollama create gemma3:1b-Q8_0 -f .\modelfile.md -q Q8_0
gathering model components
quantizing F16 model to Q8_0
Error: llama_model_quantize: 1
<!-- gh-comment-id:2718318769 --> @Hioness commented on GitHub (Mar 12, 2025): I've had the same issue with the 1b version. ```` > ollama create gemma3:1b-Q8_0 -f .\modelfile.md -q Q8_0 gathering model components quantizing F16 model to Q8_0 Error: llama_model_quantize: 1 ````
GiteaMirror commented 2026-04-22 12:59:24 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 12, 2025):

I have a fix for this, but it's not quite ready yet.

<!-- gh-comment-id:2718841166 --> @pdevine commented on GitHub (Mar 12, 2025): I have a fix for this, but it's not quite ready yet.
GiteaMirror commented 2026-04-22 12:59:24 -05:00
Author
Owner
Copy Link

@lowlyocean commented on GitHub (Mar 14, 2025):

I have a fix for this, but it's not quite ready yet.

Is this something we can test before the next official ollama release version?

<!-- gh-comment-id:2724975917 --> @lowlyocean commented on GitHub (Mar 14, 2025): > I have a fix for this, but it's not quite ready yet. Is this something we can test before the next official ollama release version?
GiteaMirror commented 2026-04-22 12:59:24 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 15, 2025):

Fixed w/ #9776

This should work in Ollama 0.6.2 (didn't make it work 0.6.1 unfortunately) or you can build from main.

<!-- gh-comment-id:2726071432 --> @pdevine commented on GitHub (Mar 15, 2025): Fixed w/ #9776 This should work in Ollama `0.6.2` (didn't make it work `0.6.1` unfortunately) or you can build from `main`.
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#32078
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?