[GH-ISSUE #1230] [Feature] Support for Qwen3MoE #837

New issue

Closed

opened 2026-10-29 14:45:08 +00:00 by bsakaguchi · 1 comment

bsakaguchi commented

2026-10-29 14:45:08 +00:00

Owner

Originally created by @sorasoras on GitHub (Apr 29, 2025).
Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1230

Checklist

1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed.
2. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-English/Chinese content without translation may be closed.

Motivation

https://github.com/QwenLM/Qwen3
https://qwenlm.github.io/blog/qwen3/
30B-A3B, 235B-A22B
Support for inference with both new model
In addition to support inference,
It would be great for allow hybrid inference between dedicated GPU like 4060 and IGPU like 780M.

https://huggingface.co/Qwen/Qwen3-30B-A3B

Originally created by @sorasoras on GitHub (Apr 29, 2025). Original GitHub issue: https://github.com/kvcache-ai/ktransformers/issues/1230 ### Checklist - [x] 1. If the issue you raised is not a feature but a question, please raise a discussion at https://github.com/kvcache-ai/ktransformers/discussions. Otherwise, it will be closed. - [x] 2. To help the community, I will use Chinese/English or attach an Chinese/English translation if using another language. Non-English/Chinese content without translation may be closed. ### Motivation https://github.com/QwenLM/Qwen3 https://qwenlm.github.io/blog/qwen3/ 30B-A3B, 235B-A22B Support for inference with both new model In addition to support inference, It would be great for allow hybrid inference between dedicated GPU like 4060 and IGPU like 780M. ### Related resources https://huggingface.co/Qwen/Qwen3-30B-A3B

bsakaguchi closed this issue

2026-10-29 14:45:08 +00:00

bsakaguchi commented

2026-10-29 14:45:08 +00:00

Author

Owner

@Atream commented on GitHub (Apr 29, 2025):

supported now! Please check readme.md

@Atream commented on GitHub (Apr 29, 2025): supported now! Please check readme.md