llamaperf
Submit

Llama2 7B

on AMD Strix Halo 128GB · llama.cpp / ROCm (build unreported)

AMD hardware
Oct 14, 2026
Share
Throughput
50.2 t/s gen · 1493.3 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q4_0 (GGUF)
Flash Attention
on
System RAM
128 GB

Summary

User reports Llama2 7B at 50.2 t/s generation and 1493.3 t/s prompt processing on an AMD Strix Halo 128GB system. Setup is llama.cpp with Q4_0, run natively on the Radeon 8060S iGPU via ROCm with -ngl 99 and flash attention; an attached RTX 5070 Ti does not participate. ROCm TG128 measured 50.16 +/- 0.07 t/s and PP512 1493.28 +/- 30.20 t/s; prompt processing fell to 958.19 t/s at 8192 tokens of context.