ROCm b9843 native PP2080 d512

on AMD Radeon 8060S integrated GPU (Strix Halo; system RAM unreported) · llama.cpp b9843 (86b94708f) / stock ROCm

Oct 13, 2026

Throughput

166.5 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

UD-IQ3_S (GGUF)

KV cache

F16

Flash Attention

Summary

User reports Mimo 2.5 at 166.5 t/s prompt processing on an AMD Ryzen AI MAX+ 395 with Radeon 8060S graphics. Setup is llama.cpp b9843 with UD-IQ3_S and f16 K/V cache, flash attention on, one participating Radeon. The 166.5 t/s figure is the stock batch2048/ubatch512 arm at depth 512, measured over three repeats of a 2080-token prompt loop; generation throughput and TTFT were not measured.