Liquid AI
Liquid AI
Liquid AI/LFM2.5-VL-450M

Runs

View all benchmark runs for this model family.

	Quant						Actions

	Quant		Actions

	Quant						Actions
M5 Max	q4_0	llama.cppb8680	753.0 tok/s	37,082.4 tok/s	0.66 GB 1%
M5 Max	q8_0	llama.cppb8680	640.8 tok/s	34,234.3 tok/s	1.00 GB 2%
M5 Max	f16	llama.cppb8680	469.0 tok/s	32,426.3 tok/s	1.17 GB 2%
GeForce RTX 5070 Ti	f16	llama.cppb1	548.7 tok/s	41,262.9 tok/s	0.98 GB 4%
M1 Max	f16	llama.cppb8640	229.8 tok/s	10,108.0 tok/s	0.24 GB 0%
M1 Max	q8_0	llama.cppb8640	256.1 tok/s	10,490.4 tok/s	0.46 GB 1%
M1 Max	q4_0	llama.cppb8640	447.3 tok/s	10,401.9 tok/s	0.18 GB 0%

	Quant		Actions
M5 Max	q4_0	753.0 tok/s
M5 Max	q8_0	640.8 tok/s
M5 Max	f16	469.0 tok/s
GeForce RTX 5070 Ti	f16	548.7 tok/s
M1 Max	f16	229.8 tok/s
M1 Max	q8_0	256.1 tok/s
M1 Max	q4_0	447.3 tok/s