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 #14297] Model request for Qwen3.5-397B-A17B local version #55818

New Issue
Open
opened 2026-04-29 09:46:22 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-29 09:46:22 -05:00
Owner
Copy Link

Originally created by @KingjZhang on GitHub (Feb 17, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14297

Model request for Qwen3.5-397B-A17B local version

Originally created by @KingjZhang on GitHub (Feb 17, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14297 Model request for Qwen3.5-397B-A17B local version
GiteaMirror added the model label 2026-04-29 09:46:22 -05:00
GiteaMirror commented 2026-04-29 09:46:23 -05:00
Author
Owner
Copy Link

@josephlugo commented on GitHub (Feb 17, 2026):

Both: thinking and non-thinking, please.

<!-- gh-comment-id:3914778085 --> @josephlugo commented on GitHub (Feb 17, 2026): Both: thinking and non-thinking, please.
GiteaMirror commented 2026-04-29 09:46:24 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 17, 2026):

https://ollama.com/frob/qwen3.5

Note that ollama doesn't support this architecture yet, either wait for the next vendor sync or build ollama as described in the model card.

The model is hybrid, so thinking is controlled with the think parameter.

<!-- gh-comment-id:3915042486 --> @rick-github commented on GitHub (Feb 17, 2026): https://ollama.com/frob/qwen3.5 Note that ollama doesn't support this architecture yet, either wait for the next vendor sync or build ollama as described in the model card. The model is hybrid, so thinking is controlled with the `think` parameter.
GiteaMirror commented 2026-04-29 09:46:24 -05:00
Author
Owner
Copy Link

@josephlugo commented on GitHub (Feb 17, 2026):

@rick-github any chance to create a model card with the “-Instruct” tag where no-think is active?

I know the ‘think’ parameter exists to control this. Main issue is n8n does not expose an option to pass this cleanly from the agent node UI (to the best of my knowledge).

<!-- gh-comment-id:3915198187 --> @josephlugo commented on GitHub (Feb 17, 2026): @rick-github any chance to create a model card with the “-Instruct” tag where no-think is active? I know the ‘think’ parameter exists to control this. Main issue is n8n does not expose an option to pass this cleanly from the agent node UI (to the best of my knowledge).
GiteaMirror commented 2026-04-29 09:46:24 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 17, 2026):

I'll create a model with think disabled. What quant level?

<!-- gh-comment-id:3915211542 --> @rick-github commented on GitHub (Feb 17, 2026): I'll create a model with think disabled. What quant level?
GiteaMirror commented 2026-04-29 09:46:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 17, 2026):

Done.

<!-- gh-comment-id:3915345425 --> @rick-github commented on GitHub (Feb 17, 2026): Done.
GiteaMirror commented 2026-04-29 09:46:25 -05:00
Author
Owner
Copy Link

@chr0n1x commented on GitHub (Feb 25, 2026):

unsure if this goes without saying - but I'm looking forward to qwen35 and qwen35moe support. thanks to everyone that will make / is making this happen!

<!-- gh-comment-id:3956291899 --> @chr0n1x commented on GitHub (Feb 25, 2026): unsure if this goes without saying - but I'm looking forward to `qwen35` and `qwen35moe` support. thanks to everyone that will make / is making this happen!
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#55818
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?