Text Models
LFMs deliver powerful performance in a lightweight, customizable, and compute-efficient footprint for deployment in any environment.
Models built for real-world constraints.
Frontier-grade intelligence at a fraction of the compute, on any hardware, on or off the cloud.
Explore LFMs
Decision Models
Purpose-built models for classification, routing, and scoring. One API call returns calibrated probabilities across a fixed set of outcomes.
Audio Model
End-to-end foundation model for audio and text generation. Designed for low latency, it enables responsive, high-quality conversations with only 1.5 billion parameters.
Nano Models
Tiny customized models for specific tasks and knowledge.
- LFM2.5-Encoder-350M-PII-Detector
- LFM2.5-Encoder-350M
- LFM2.5-Encoder-230M
- LFM2.5-Embedding-350M
- LFM2.5-ColBERT-350M
- LFM2.5-VL-450M-Extract
- LFM2.5-VL-1.6B-Extract
- LFM2-2.6B-Longevity
- LFM2-1.2B-Longevity
- LFM2-350M-Math
- LFM2-350M-PII-Extract-JP
- LFM2-2.6B-Transcript
- LFM2-350M-ENJP-MT
- LFM2-2.6B-MMAI
Every LFM is free to download, run, and fine-tune — including commercially — until your company passes $10M in annual revenue. See pricing & licensing
On-device performance for
Explore more quants, runtimes, modalities, and metrics on Pipette.
Deploy anywhere
Local AI
GGUF, MLX, and ONNX builds run on laptops, phones, and edge boxes with no key.
Liquid API
The fastest way to start. Get a key from Liquid Console, then call our models over an OpenAI-compatible endpoint.
GPU serving
Serve many requests at once. Run your own GPU server, or let a platform handle the hardware.
