llamaperf

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

on Unknown GPU

Tone: positive
Oct 3, 2026
Throughput
29-46.7 t/s gen · 1010-1178 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Summary

User reports testing an unpublished engine on Qwen3.8 Flash-Next locally, with reading at 1,010–1,178 t/s and writing at 29–46.7 t/s. The model is a GGUF build (PaoAI STRIX BALANCED 2). The engine is not yet published and is still in testing. The user says the results are promising and that it took 2 turns to build a Pocket Map.