Qwen
Qwen
Qwen/Qwen3-0.6B

Runs

View all benchmark runs for this model family.

	Quant
M1 Max	4bit	mlx_lm0.31.1	163.6 tok/s	2,279.1 tok/s	2.13 GB 3%
M1 Max	q8_0	llama.cppb8240	98.7 tok/s	2,281.0 tok/s	1.26 GB 2%
M1 Max	4bit	mlx_lm0.31.0	151.6 tok/s	1,895.0 tok/s	2.13 GB 3%
M1 Max	q8_0	llama.cppb8240	119.2 tok/s	3,233.4 tok/s	1.26 GB 2%