[GH-ISSUE #15625] qwen3.6 seems interesting , when will be available in ollama/llama.cpp #72029

Closed
opened 2026-05-05 03:21:50 -05:00 by GiteaMirror · 5 comments
Owner

Originally created by @liaoweiguo on GitHub (Apr 16, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15625

waiting

Originally created by @liaoweiguo on GitHub (Apr 16, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15625 waiting
GiteaMirror added the feature request label 2026-05-05 03:21:50 -05:00
Author
Owner

@rick-github commented on GitHub (Apr 16, 2026):

https://ollama.com/library/qwen3.6

<!-- gh-comment-id:4261281239 --> @rick-github commented on GitHub (Apr 16, 2026): https://ollama.com/library/qwen3.6
Author
Owner

@fcorneli commented on GitHub (Apr 16, 2026):

Tried out qwen3.6, wow...

<!-- gh-comment-id:4261538377 --> @fcorneli commented on GitHub (Apr 16, 2026): Tried out qwen3.6, wow...
Author
Owner

@OracleToes commented on GitHub (Apr 17, 2026):

https://ollama.com/library/qwen3.6

It still won't run gguf models from huggingface, journalctl gives the log:
llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35moe'
I used the unsloth gguf of qwen3.6 as well as tried a few other models and none worked.

<!-- gh-comment-id:4264729555 --> @OracleToes commented on GitHub (Apr 17, 2026): > https://ollama.com/library/qwen3.6 It still won't run gguf models from huggingface, journalctl gives the log: `llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'qwen35moe'` I used the unsloth gguf of qwen3.6 as well as tried a few other models and none worked.
Author
Owner

@fcorneli commented on GitHub (Apr 17, 2026):

The following works:

uname -o -r -m
6.12.0-124.47.1.el10_1.x86_64 x86_64 GNU/Linux
ollama --version
ollama version is 0.20.7
ollama run qwen3.6:35b-a3b-q8_0 "Hi"
<!-- gh-comment-id:4265823228 --> @fcorneli commented on GitHub (Apr 17, 2026): The following works: ``` uname -o -r -m 6.12.0-124.47.1.el10_1.x86_64 x86_64 GNU/Linux ollama --version ollama version is 0.20.7 ollama run qwen3.6:35b-a3b-q8_0 "Hi" ```
Author
Owner

@rick-github commented on GitHub (Apr 18, 2026):

Please stop shilling your models. Users can find them through the search function.

<!-- gh-comment-id:4273955764 --> @rick-github commented on GitHub (Apr 18, 2026): Please stop shilling your models. Users can find them through the search function.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#72029