llamaperf
Submit

Qwen3.8 Flash-Next, Gufo uncached 2048/512 (Sep 28)

on AMD Strix Halo 128GB · Gufo · 262,144 ctx

AMD hardware
Oct 11, 2026
Throughput
71.1 t/s gen · 1488.7 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
UD-Q4_K_XL (GGUF)
MTP (Multi-Token Prediction)
on
System RAM
128 GB

Summary

User reports Qwen3.8 at 71.1 t/s generation and 1488.7 t/s prompt processing on an AMD Strix Halo 128GB system. Setup is Gufo with UD-Q4_K_XL, a 262,144-token configured context, 512-token prefill chunks and MTP ceiling 7 with a shared Q8 MTP head. The run used 2,048 new prompt tokens at depth zero and 512 generated tokens, with 447 drafted and 447 accepted tokens; the exact rates were 1,488.66 PP and 71.08 TG.