Qwen3.6 27B Heretic-v2
on NVIDIA RTX 4090 · llama.cpp · 262,000 ctx
May 9, 2026
Summary
User reports MTP draft acceptance of about 73%.
Setup is a TBQ4_0 KV cache with an MTP draft of 3, using a fork of llama.cpp.
on NVIDIA RTX 4090 · llama.cpp · 262,000 ctx