Qwen

/

Qwen3-Next-80B-A3B-Instruct

like 855

Follow

Qwen 56.6k

Hi, and thanks for sharing the new Qwen3-Next-80B-A3B-Instruct model — it looks really impressive.

Since this release is very new (just announced recently), I was wondering:
-Do you plan to release smaller Qwen3-Next variants (e.g., 7B, 14B, 32B) with the same architecture in the near future?

This would be very useful for researchers and developers who don’t have access to the compute needed for 80B models but still want to benefit from the new Hybrid Attention + MoE + MTP architecture.

Thanks!