LFM3 Omni 2B

Liquid AI · 2.17B parameters · Language models

Weights and memory

9 options
FormatFile sizeYour deviceLink
Q4_01.0 GB1.9 GB ◇Hugging Face
1.1 GB1.9 GB ◇Hugging Face
1.8 GB2.6 GB ◇Hugging Face
3.5 GB4.2 GB ◇Hugging Face
F163.5 GB4.2 GB ◇Hugging Face
4-bit2.1 GB2.9 GB ◇Hugging Face
8-bit2.9 GB3.6 GB ◇Hugging Face
4.5 GB5.1 GB ◇Hugging Face
—4.5 GB5.1 GB ◇Hugging Face

Published by the lab. File size is what the repository lists; for original weights it is the total of the weight files, which can include more than one variant. ● memory stated by the publisher · ◇ estimate from file size, an 8K-token context and 0.5 GB for the runtime. Unknown means there is no figure to go on. Checked 2026-11-02.

Tests on this site

Not tested yet

This site has not run this model. How tests are run