Qwen3.6-35B-A3B-FP8

Qwen3.6-35B-A3B-FP8 is a quantized FP8 checkpoint of Alibaba's Qwen3.6-35B-A3B sparse mixture-of-experts model, featuring 35B total parameters with approximately 3B active per token. It targets efficient inference for coding, tool use, long-context reasoning, and multimodal tasks including text, image, and video inputs. Source: supabase.