Qwen 3.6

Apr 2026

Alibaba's next-gen natively multimodal reasoning models. Dense and MoE variants that rival models many times their size on coding and vision tasks.

Sizes

Show smaller quantizations

Qwen 3.6 27B Q8_0 requires 48 GB+ memory	28.6 GB
Qwen 3.6 35B-A3B Q8_0 requires 64 GB+ memory	36.9 GB