llamaperf
Oct 9, 2026
Throughput
16.3 t/s gen · 484.6 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8 (GGUF)
System RAM
128 GB

Summary

User reports DeepSeek V4 Flash at 484.62 t/s prefill and 16.28 t/s decode on a Strix Halo 128GB (Ryzen AI MAX+ 395, Radeon 8060S, gfx1151). Setup is Gufo with an IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8 mixed GGUF, one session, speculative decoding disabled, thinking off, temperature 0, seed 1, nominal pp2048/tg128 (2,035 prompt tokens, 128 generated). One warmed sample; no standard deviation reported. The maintainer notes target-model quality parity is unestablished and build-sensitive differences are under investigation. Power, KV-cache type, Flash Attention and peak memory were not reported.