by Liquid AI

LFM2.5-2.6B.

text open weights edge 3B params 131K ctx
Smallest GPU
1× Nvidia GeForce GTX 1650
$0.051/hr
Run it yourself

Cheapest hardware per quantisation.

Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/小时为当前最低报价。多卡配置在有同规格实例出租时使用真实实例价格,否则为单卡价格乘以卡数。

Quantisation Cheapest GPU config Total VRAM Live $/hr tokens/sec
FP16
FP16 — half precision (default)
12 GB $0.038/hr
Nosana · 按需
46.7 Compare →
FP8
FP8 — 8-bit float (Hopper / Blackwell)
4 GB $0.051/hr
Vast.ai · 按需
33.2 Compare →
Just need an API?
Skip the GPU rental and call a hosted endpoint instead. See access providers on the Overview tab →