Qwen 3.6 (35B-A3B, Q8)

Alibaba's Qwen 3.6 at 35B total parameters with only 3B active per token (Mixture-of-Experts: 256 experts, 8 routed + 1 shared), 8-bit quantization for higher fidelity than the Q4 build (at roughly double the memory footprint). Multimodal (text + image + video), 256K native context (extensible to ~1M with YaRN), explicit native tool-calling support.

Gezel downloads this model the first time a gezel needs it, checks the file against its published hash, and applies tuned settings for it.

The model’s own page · Every model · Model scorecard