Qwen3.8 27B

on AMD MI50 32GB · llama.cpp · 120,000 ctx

Sep 7, 2026

Throughput

13.6 t/s gen · 379.2 tokens/s prompt processing (prefill)Prompt processing measures input prefill speed; it does not tell you the time to first token.

VRAM reported

32 GB

Summary

User reports a fork optimized for AMD gfx906 (MI50/MI60/Radeon VII) reaching 379.2 t/s prefill versus 332.3 t/s (+14.1%), 252.6 t/s versus 231.1 t/s on a 120k-context fill (+9.3%), and 13.6 t/s versus 13.5 t/s deep-context TG. DFlash acceptance is 0.691.

View source ↗