Qwen3.8 27B

on NVIDIA RTX 5090 · SGLang

Sep 7, 2026

Throughput

200.0 t/s gen

Quant

NVFP4

VRAM reported

32 GB

Summary

User reports Qwen3.8-27B at over 200 t/s decode on an RTX 5090 and an RTX Pro 6000, and 38 t/s on a DGX Spark. Setup is NVFP4 with DSpark on day-0 support. The user also mentions an H200 in the cookbook link.

View source ↗