Qwen3 Coder 480B A35B Instruct MaaS

This model is a mixed int4 model with group_size 64 and symmetric quantization of Qwen/Qwen3-Coder-480B-A35B-Instruct generated by intel/auto-round via **RTN** (no algorithm tuning). Non expert layers fallback to 8 bits and group_size 128. mlp.gate layers fallback to 16 bits to ensure runing successfully on vLLM.

• Tool Use