qwen3-coder-next-fp8-sglang

sglangtorch@sparkrun-transitional

Qwen3 Coder Next (upstream FP8 quant) -- cluster only

Quick Info

Runtimesglang (torch)

Tensor Parallel2

Nodes2+

Parameters80B

Dtypefp8

Containerscitrera/dgx-spark-sglang:0.5.9-t5

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

sparkrun run @sparkrun-transitional/qwen3-coder-next-fp8-sglang