LFM2 Models — Hardware Requirements

5 LFM2 models from Liquid AI and the community, from the smallest that runs in 0.5 GB of VRAM up to 23.8B parameters. Every row links to full quantization tables and GPU compatibility.

All LFM2 Models by Size

ModelParamsContext
LFM2 350M Extract354M128K
LFM2 1.2B RAG1.2B128K
LFM2 1.2B Extract1.2B128K
LFM2 8B A1B8.3B128K
LFM2 24B A2B23.8B128K

Frequently Asked Questions

How much VRAM do I need to run a LFM2 model?
The smallest LFM2 model, LFM2 350M Extract, runs from 0.5 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
Which LFM2 models can I run on a 16 GB GPU?
5 of 5 LFM2 models fit in 16 GB of VRAM at some quantization, including LFM2 24B A2B, LFM2 8B A1B, LFM2 1.2B RAG.
What is the most popular LFM2 model to run locally?
LFM2 24B A2B is the most downloaded LFM2 model in local-friendly quantized formats. It runs from 7.0 GB of VRAM.