Inference model · QWEN

Qwen 3.5 122B A10B

Step up when 30B-class isn't enough. 256K context, 10B active. Reserve for the work that earns it.

Request Qwen 3.5 122B A10B access Back to catalog

Qwen 3.5 122B A10B sits in our catalog as the “scale up when you need to” option. Bigger active parameter count, deeper knowledge, and a 256K context window for long-document or multi-turn workflows that overflow 128K.

When to pick it

  • Long-document reasoning, contract review, multi-source synthesis
  • Multi-turn agent loops that accumulate enough context to push past 128K
  • Final-pass quality gate on top of cheaper draft models

When to look elsewhere

  • High-volume cheap inference → Gemma 4 26B A4B or DeepSeek V4 Flash
  • Tasks where 27B dense already gets you 95% of the answer