Qwen3 32B

on AMD Strix Halo 128GB · llama.cpp 1d49ca3 (author-reported) / ROCm 7

Oct 14, 2026

Throughput

6.4 t/s gen · 51.1 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

Quant

Q8_0 (GGUF)

Flash Attention

System RAM

128 GB

Summary

User reports Qwen3-32B at 6.4 t/s generation and 51.1 t/s prompt processing on an AMD Strix Halo 128GB system. Setup is llama.cpp with Q8_0 and flash attention enabled, ngl 99, on one ROCm device (gfx1151). The figures are separate llama-bench phases: PP512 at 51.12 +/- 0.24 t/s and TG128 at 6.39 +/- 0.01 t/s, not a same-request pair. Context depth is not printed.