Qwen
Qwen
Qwen/Qwen3-Coder-30B-A3B-Instruct

Runs

View all benchmark runs for this model family.

	Quant
M4 Max	4bit	mlx_lm0.31.1	88.4 tok/s	1,229.8 tok/s	18.00 GB 50%
M2	4bit	mlx_lm0.31.1	22.8 tok/s	147.8 tok/s	17.00 GB 71%

	Quant		Actions
M4 Max	4bit	88.4 tok/s
M2	4bit	22.8 tok/s