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

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

Oct 10, 2026

Throughput

35.0 t/s gen · 1701.6 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)

System RAM

128 GB

Summary

User reports Qwen3.8 Flash-Next at 35 t/s generation and 1701.6 t/s prefill on a 126,000-token prompt on an AMD Strix Halo 128GB. Setup is 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.