Qwen
Qwen
Qwen/Qwen3.5-2B

Runs

View all benchmark runs for this model family.

	Quant
M5 Max	q6_k	llama.cppb8350	171.7 tok/s	3,849.3 tok/s	0.34 GB 0%
M1 Max	6bit	mlx_lm0.31.0	96.7 tok/s	1,095.4 tok/s	3.14 GB 5%

	Quant		Actions
M5 Max	q6_k	171.7 tok/s
M1 Max	6bit	96.7 tok/s