Qwen3.6 27B
on AMD Strix Halo 128GB · llama.cpp
Summary
User reports MTP enabled with --spec-type draft-mtp --spec-draft-n-max 3.
Baseline without MTP is 11.7 tok/s.
Q8_0 was also tested: 7.4 → 18.1 tok/s (2.44×).
on AMD Strix Halo 128GB · llama.cpp