Qwen3.6 27B
on M2 Max 96GB · llama.cpp · 262,144 ctx
Use cases
codingagentic
Summary
User reports MTP speculative decoding gives a 2.5x speedup on an M2 Max 96GB.
Setup is Q5_K_M quant with a q4_0 KV cache.
The user also provides hardware recommendations for various Apple Silicon and NVIDIA GPUs.