Qwen3.6 35B (3B active)
on NVIDIA CMP 170HX 64GB (unlocked) · llama.cpp · 262,144 ctx
Sep 7, 2026
Summary
User reports Qwen3.6-35B-A3B at 63 t/s on 4x CMP 170HX 8GB cards flashed to 64GB each, 256GB total.
Setup uses MTP with little-MoE default.
Generation reaches 110 t/s with MTP optimistic.