Qwen3.6 27B
M2 Max 96GB · llama.cpp
- quant:
- Q4_K_M (gguf)
vision
Champion model in vision benchmark. Best quality and stability with thinking disabled. 90/90 successful runs. Speed: 70 s/img. Tested on Apple M2 Max 96GB with llama.cpp b9690.
M2 Max 96GB
APPLE · 96GB unified memory · 3 reports
Qwen3.6 27B
M2 Max 96GB · llama.cpp · 256,000 ctx
- throughput:
- 8.0 t/s gen
- quant:
- F16 (gguf)
- mtp (multi-token prediction):
- on
codingagentic
User benchmarked Qwen 3.6 27b F16 on M2 Max 96GB using llama.cpp with MTP speculative decoding. Generation speed varied 8-18 tok/s depending on task; without MTP got 6.6 tok/s. Used for agentic coding to create a Pacman game. Also tested Q8 quant but results were worse. Context up to 150k+ tokens usable. Chat template fixes were critical.
Qwen3.6 27B
M2 Max 96GB · llama.cpp · 262,144 ctx
- throughput:
- 28.0 t/s gen
- quant:
- Q5_K_M (gguf)
- kv:
- Q4
codingagentic
MTP speculative decoding gives 2.5x speedup. Tested on M2 Max 96GB with Q5_K_M quant and q4_0 KV cache. Also provides hardware recommendations for various Apple Silicon and NVIDIA GPUs.