Qwen3.6 35B (3B active)
on NVIDIA RTX 5070 Ti Laptop 12GB · llama.cpp · 4,096 ctx
Use cases
codingmath
Summary
User compares Qwen3.8 27B dense at Q2 and Q3 against Qwen3.6 35B-A3B MoE on 12 GB of VRAM.
The MoE was fastest and passed a sanity test, while dense Q3 ran at 7.5-9.1 t/s.
The user prefers the MoE for local use.