Qwen3.6 35B (3B active)
on NVIDIA RTX 3060 12GB · llama.cpp · 32,768 ctx
May 9, 2026
Use cases
coding
Summary
User reports llama-bench results of about 914 t/s for pp512 and about 46.8 t/s for tg128.
A practical coding profile at 32k context generates at about 43.4 t/s.
MTP gave about 47.7 t/s, a 2% improvement.