Qwen
Qwen
Qwen/Qwen3.5-35B-A3B

Runs

View all benchmark runs for this model family.

	Quant
M4 Max	4bit	mlx_lm0.31.2	104.0 tok/s	1,461.7 tok/s	21.00 GB 58%
M4 Max	q4_k_m	llama.cppb8680	60.1 tok/s	1,099.2 tok/s	20.65 GB 57%
M2 Max	4bit	mlx_lm0.31.1	62.5 tok/s	509.3 tok/s	21.00 GB 22%
M4 Max	4bit	mlx_lm0.31.1	105.1 tok/s	1,412.7 tok/s	21.00 GB 58%
M4 Pro	APEX-Compact	llama.cppb8793	48.4 tok/s	703.1 tok/s	16.81 GB 26%
M4 Max	q4_k_m	llama.cppb8500	79.5 tok/s	1,235.2 tok/s	21.24 GB 33%
M5 Max	q4_k_m	llama.cppb8350	94.9 tok/s	1,378.0 tok/s	0.43 GB 0%
M1 Max	4bit	mlx_lm0.31.0	60.1 tok/s	393.7 tok/s	21.00 GB 33%
M1 Max	4bit	mlx_lm0.31.0	55.7 tok/s	379.9 tok/s	21.00 GB 33%