Qwen 3.8 (27B, Q8)

Alibaba's Qwen 3.8 at 27B parameters: a dense, multimodal agentic model with native text, image, and video understanding, 262K context, flexible reasoning effort, MTP, and native tool calling. Q8_0 and 8-bit MLX preserve more fidelity than the Q4 build at roughly double the memory footprint; intended for machines with 40GB+ usable memory.

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