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 #14434] q8_0 for Qwen-3.5? #55885

New Issue
Closed
opened 2026-04-29 09:53:04 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-29 09:53:04 -05:00
Owner
Copy Link

Originally created by @chigkim on GitHub (Feb 26, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14434

Can we also have q8_0, or bfp16, so we can quantize?
The library shows only q4_K_M.
https://ollama.com/library/qwen3.5/tags
Thanks so much!

Originally created by @chigkim on GitHub (Feb 26, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14434 Can we also have q8_0, or bfp16, so we can quantize? The library shows only q4_K_M. https://ollama.com/library/qwen3.5/tags Thanks so much!
GiteaMirror added the model label 2026-04-29 09:53:04 -05:00
GiteaMirror commented 2026-04-29 09:53:32 -05:00
Author
Owner
Copy Link

@Maltz42 commented on GitHub (Feb 27, 2026):

I'd like to see some local quants of 397B-A17B as well. I'm specifically after Q6_K, but there are usually a large variety of quants and model sizes. It does seem odd that the selection is so limited on such an in-demand model.

<!-- gh-comment-id:3973959897 --> @Maltz42 commented on GitHub (Feb 27, 2026): I'd like to see some local quants of 397B-A17B as well. I'm specifically after Q6_K, but there are usually a large variety of quants and model sizes. It does seem odd that the selection is so limited on such an in-demand model.
GiteaMirror commented 2026-04-29 09:53:32 -05:00
Author
Owner
Copy Link

@ryanmon1 commented on GitHub (Feb 28, 2026):

I'd like to see some local quants of 397B-A17B as well. I'm specifically after Q6_K, but there are usually a large variety of quants and model sizes. It does seem odd that the selection is so limited on such an in-demand model.

Pull it from hugging face

<!-- gh-comment-id:3976639263 --> @ryanmon1 commented on GitHub (Feb 28, 2026): > I'd like to see some local quants of 397B-A17B as well. I'm specifically after Q6_K, but there are usually a large variety of quants and model sizes. It does seem odd that the selection is so limited on such an in-demand model. Pull it from hugging face
GiteaMirror commented 2026-04-29 09:53:33 -05:00
Author
Owner
Copy Link

@chigkim commented on GitHub (Feb 28, 2026):

You can't seem to use models from hugging face: unknown model architecture: 'qwen35moe'
https://github.com/ollama/ollama/issues/14512

<!-- gh-comment-id:3977317068 --> @chigkim commented on GitHub (Feb 28, 2026): You can't seem to use models from hugging face: `unknown model architecture: 'qwen35moe'` https://github.com/ollama/ollama/issues/14512
GiteaMirror commented 2026-04-29 09:53:33 -05:00
Author
Owner
Copy Link

@MrLafarge commented on GitHub (Feb 28, 2026):

You can't seem to use models from hugging face: unknown model architecture: 'qwen35moe' #14512

That issue has been fixed and merged with main, see here: #14503 . So in the next version it should work.

<!-- gh-comment-id:3978233977 --> @MrLafarge commented on GitHub (Feb 28, 2026): > You can't seem to use models from hugging face: `unknown model architecture: 'qwen35moe'` [#14512](https://github.com/ollama/ollama/issues/14512) That issue has been fixed and merged with main, see here: #14503 . So in the next version it should work.
GiteaMirror commented 2026-04-29 09:53:33 -05:00
Author
Owner
Copy Link

@chigkim commented on GitHub (Mar 1, 2026):

Hopefully 35b is also coming soon as well! :)
It seems like q8_0 and bf16 for 27b are uploaded 7 hours ago.
https://ollama.com/library/qwen3.5/tags

<!-- gh-comment-id:3979086686 --> @chigkim commented on GitHub (Mar 1, 2026): Hopefully 35b is also coming soon as well! :) It seems like q8_0 and bf16 for 27b are uploaded 7 hours ago. https://ollama.com/library/qwen3.5/tags
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 model
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#55885
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?