Qwen: Qwen3.5-122B-A10B

Qwen

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.

Other versions in the Qwen family

Qwen/QwQ-32B-AWQ

32B

Qwen/Qwen-7B-Chat

7B

Qwen/Qwen1.5-7B

7B

Qwen/Qwen1.5-MoE-A2.7B

2.7B

Qwen/Qwen2-0.5B

0.5B