llamaperf
Submit

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

on AMD Strix Halo 128GB · Strata · 126,000 ctx

AMD hardware
Oct 11, 2026
Throughput
42.7 t/s gen · 1294.2 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
UD-IQ4_XS (GGUF)
MTP (Multi-Token Prediction)
on

Use cases

long-context

Summary

User reports Qwen3.8 Flash-Next at 42.7 t/s generation and 1294.2 t/s prefill on a 126,000-token prompt on an AMD Strix Halo 128GB. Setup is Strata at UD-IQ4_XS with speculative decoding on, one request. tomasreminek's context-131072 request of 2026-10-06. A source-reported measurement, not independently reproduced.