llamaperf

Qwen3.8 125B (6B active) Flash-Next

on Bosgame M5 · Gufo · 256,000 ctx

Tone: positive
Oct 21, 2026
Throughput
72.6 t/s gen · 1405.0 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Summary

User reports Qwen3.8-Flash-Next at 1,405 t/s prefill and 72.6 t/s decode at 256K context on a Bosgame M5 mini PC running Windows 11. Setup is a Windows port of Gufo, patched with improvements from the upstream Linux repository; the user says each port was benchmarked and regression-tested. Peak figures were 1,601 t/s prefill and 75.4 t/s decode with MTP speculation enabled.