Text Models
LFMs deliver powerful performance in a lightweight, customizable, and compute-efficient footprint for deployment in any environment.
Liquid Foundation Models
Models built for real-world constraints.
We’ve redefined what’s possible, designed for efficiency, speed, and real-world deployment on any device.
From wearables to robotics, phones, laptops, cars, and more, LFMs run seamlessly on GPUs, CPUs, or NPUs, making intelligence accessible everywhere.
Explore LFMs
Frontier-grade intelligence at a fraction of the compute, on any hardware, on or off the cloud.
Every LFM is free to download, run, and fine-tune — including commercially — until your company passes $10M in annual revenue. See pricing & licensing
Vision-Language Models
Multimodal models using vision and text inputs and outputs with capabilities designed for low latency and device aware deployment.
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
Decision Models
Purpose-built models for classification, routing, and scoring. One API call returns calibrated probabilities across a fixed set of outcomes.
Run it 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.
Built for efficient inference everywhere you need it.
Unmatched speed, quality, and memory-efficiency on the edge, or in the cloud.
Whether deploying on smartphones, laptops, vehicles, or any other device, LFMs run efficiently on CPU, GPU, and NPU hardware. Designed for millisecond latency, on-device resilience, and data privacy, LFMs unlock the full potential of local, cloud, and hybrid AI across industries.
Decode throughput on Galaxy S26 Ultra · SM8850 · CPU · llama.cpp b10216 · Android · Q4_K_M
Data provided by Pipette. Open this exact view on Pipette for more models and filters.
