Liquid AI
Liquid AI
Liquid AI/LFM2.5-350M

Runs

View all benchmark runs for this model family.

	Quant
GeForce RTX 5070 Ti	f16	llama.cppb1	547.3 tok/s	40,543.3 tok/s	0.66 GB 3%
M1 Max	f16	llama.cppb8640	239.0 tok/s	8,178.6 tok/s	1.69 GB 3%
M1 Max	q4_0	llama.cppb8640	389.1 tok/s	7,868.0 tok/s	0.79 GB 1%
M4 Pro	q8_0	llama.cppb8680	293.1 tok/s	7,251.8 tok/s	0.43 GB 2%
M3	q4_k_m	llama.cppb8670	258.3 tok/s	3,399.3 tok/s	0.44 GB 2%
M3	q8_0	llama.cppb8670	151.5 tok/s	3,544.2 tok/s	1.69 GB 7%
M1 Max	q8_0	llama.cppb8640	274.3 tok/s	10,369.4 tok/s	1.27 GB 2%
M4 Pro	q8_0	llama.cppb8793	355.9 tok/s	8,786.3 tok/s	0.95 GB 1%