MODEL REFERENCE / Qwen

Qwen/Qwen3.5-35B-A3B

Compact Qwen3.5 multimodal MoE (35B total / 3B active) with gated delta networks, 256 experts, and 262K context

Compact Qwen3.5 MoE — single-GPU FP8, 2x GPU or 2x Xeon 6 NUMA nodes or 4x Intel Arc Pro B60/B70 BF16 serving

vLLMmoe35B / 3B262,144 ctxvLLM 0.17.0+multimodaltext

02 / Configure

Configure serving

Choose engine, hardware and deployment options. The command updates as you go.

03 / Understand

Model notes and examples