Qwen3.8-27B hits 206 tok/s on single RTX 5090 via SGLang

StefanoGogioso · x · 2026-08-17

SGLang announces Day-0 support for the Qwen3.8-27B model. Benchmarks show decoding speeds of 206.1 tok/s on a single RTX 5090 with NVFP4 and DSpark, and 38.28 tok/s on DGX Spark. The model excels at agentic planning and long-horizon tasks, with strong capabilities in 3D, game design, and coding.

Original post →

More from Infra

Infra channel →