Qwen3.6 27B
on NVIDIA V100 32GB · llama.cpp · 200,000 ctx
May 6, 2026
Use cases
codingtool-use
Summary
User reports 29-30 t/s without MTP and 54-55 t/s with MTP on the MTP branch of llama.cpp by am17an, at a 150W power limit.
The model is used as a VSCode Copilot backend.
Throughput falls to 40-45 t/s after 50k tokens.