How much does LFM2-8B-A1B cost?

LFM2-8B-A1B costs $0.01 per million input tokens and $0.02 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.000 per message.

What benchmarks has LFM2-8B-A1B been tested on?

LFM2-8B-A1B has not been benchmarked yet. Scores are added as benchmarks are published.

Is LFM2-8B-A1B open source?

Yes, LFM2-8B-A1B is open source.

How does LFM2-8B-A1B compare to 3b De Ft Research_release?

LFM2-8B-A1B has an average score of 0.0 while 3b De Ft Research_release scores 0.0. 3b De Ft Research_release slightly outperforms LFM2-8B-A1B overall. See full comparison →

Home/Models/LFM2-8B-A1B

LFM2-8B-A1B

Name: LFM2-8B-A1B
Price: 0.01 USD
Author: liquid

by liquid · Released Oct 2025

Open Source

Compare

Context

33K tokens (~16 books)

Input $/1M

$0.01

Output $/1M

$0.02

Type

text

License

Open Source

Benchmarks

0 tested

Data updated today

About

LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.

No benchmark data available yet.

Similar Models

3b De Ft Research_release

Canopy Labs

0.0TBD

3b Ko Ft Research_release

Links