llamaperf

Qwen3.8 27B

on 4× AMD Radeon Pro V620 32GB

Tone: mixedAMD hardware
Sep 7, 2026
Throughput
30.0 t/s gen · 1000-1300 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.
Quant
Q8

Summary

User reports Qwen3.8 27B at Q8 running at 30 t/s with 1-1.3k t/s prefill on a Threadripper 3975WX with four Radeon Pro V620 cards. User measures electricity rather than speed: about 0.8-0.85 kW during inference and 0.15-0.2 kW idle, which at 0.32 dollars per kWh works out to roughly 55-60 dollars a month for six hours of inference a day. User calls 30 t/s pretty slow and reports 3.5k prefill and 70-80 t/s on Qwen3.6 35B instead.