Liquid AI
Liquid AI
Liquid AI/LFM2-1.2B-Extract

Runs

View all benchmark runs for this model family.

	Quant						Actions

	Quant		Actions

	Quant						Actions
M1 Max	f16	llama.cppb8640	89.2 tok/s	2,098.8 tok/s	2.67 GB 4%
TITAN Xp2×	f16	llama.cppb1	153.8 tok/s	4,088.9 tok/s	2.52 GB 8%
TITAN Xp2×	f16	llama.cppb1	156.2 tok/s	4,109.3 tok/s	2.52 GB 8%

	Quant		Actions
M1 Max	f16	89.2 tok/s
TITAN Xp2×	f16	153.8 tok/s
TITAN Xp2×	f16	156.2 tok/s