Qwen3.8 27B
on AMD Strix Halo 128GB · llama.cpp · 98,304 ctx
Use cases
codingcreative-writinglong-context
Summary
User reports Qwen3.8-27B at 59.7 tok/s cold (c30) on AMD Strix Halo (Ryzen AI Max+ 395, Radeon 8060S, 64GB unified).
Setup is llama.cpp b10435-era with UD-Q4_K_XL GGUF, F16 KV cache, 96k context, draft-mtp + ngram-mod speculation (n-max 12, n-min 24).
Warm c30 reaches 148-163 tok/s but is labeled a repetition artifact; real conversational traffic is 11-24 tok/s (prose) and 30-40 tok/s (code). Prefill is 271-330 tok/s by depth. Time-per-task is 7.9-14.3s (median 11.3).