Qwen3.8 27B
on AMD RX 7900 XTX · llama.cpp · 262,144 ctx
Oct 4, 2026
Use cases
tool-use
Summary
User reports Qwen3.8-27B at 44.5 tok/s decode and 404 tok/s prefill on an RX 7900 XTX 24GB.
Setup is llama.cpp (ROCm host build b11160 for gfx1100) with IQ3_S GGUF weights and q8_0/q5_1 KV cache, running the full 262,144-token window with MTP speculation on.
Context gate recalled at 213,570 prompt tokens in 528.7 s. Paired MTP measurements for this launch are spec-off 11.2 tok/s versus 23.3 tok/s at 240K fill. The desktop shares about 1.2 GiB of the card, so a headless box may decode slightly faster.