Qwen
Qwen
Qwen/Qwen3-1.7B

Runs

View all benchmark runs for this model family.

	Quant
M3 Ultra	4bit	mlx_lm0.31.1	251.1 tok/s	4,899.4 tok/s	2.96 GB 1%
M5 Pro	4bit	mlx_lm0.31.2	150.9 tok/s	7,366.3 tok/s	2.84 GB 4%
M5 Pro	4bit	mlx_lm0.31.2	146.3 tok/s	7,319.5 tok/s	2.78 GB 4%
M1 Max	4bit	mlx_lm0.31.0	113.5 tok/s	1,053.3 tok/s	2.58 GB 4%