Qwen3.6-35B-A3B

Alibaba llm

Sparse sibling of Qwen3.6: 35B total with 3B active per token, thinking mode on by default.

overall ⌄

47.1

43 of 93 ranked

price · $/M tokens

self-hosted

open weights, no first-party API

to run it yourself ⌄

21 GB

minimum · 84 GB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

No recorded lineage — root or standalone model.