Mac Studio (M4 Max)

Apple · 64 GB VRAM

3recorded runs

226.9best tok/s

3sourced

How it compares — 64 GB tier

Best verified tok/s per GPU in this VRAM tier — compare any two like-for-like.

Evidence: 3 sourced runs · 1 independent source · first recorded Oct 14, 2026. What these labels mean.

GPU	Model	Quant	Backend	Ctx	tok/s	prompt tok/s	VRAM GB	Source
Mac Studio (M4 Max) · 64 GB	Qwen3.6-35B-A3B	Q4_K_XL	llama.cpp 781dbc5	1000	226.9 ✓	—	—	src
Mac Studio (M4 Max) · 64 GB	Qwen3.6-35B-A3B	Q4_K_XL	llama.cpp 781dbc5	4000	220.2 ✓	—	—	src
Mac Studio (M4 Max) · 64 GB	Qwen3.6-35B-A3B	Q4_K_XL	llama.cpp 781dbc5	400	207.6 ✓	—	—	src