Model Recipes
Qwen

Qwen/Qwen3-Coder-480B-A35B-Instruct

Large coder MoE with 480B total / 35B active parameters, strong tool-use and code generation capabilities.

HumanEval 0.939, MBPP 0.918 (FP8). Recommended FP8 on 8x H200/H20 via DP=8

moe480B / 35B262,144 ctxvLLM 0.10.0+text
Guide