qwen3.5-35b-a3b-fp8-sglang

sglangtorch@sparkrun-transitional

Qwen3.5 35B A3B (upstream, FP8 quant) SGLang

Quick Info

Runtimesglang (torch)

Tensor Parallel1

Nodes1+

Dtypefp8

Containerscitrera/dgx-spark-sglang:0.5.9-dev1-329817e2-t5

Tensor Parallel (--tp)GPU Memory (--gpu-mem)Port (--port)Served Model Name

sparkrun run @sparkrun-transitional/qwen3.5-35b-a3b-fp8-sglang