TextImage + textVoice assistants

Liquid LFM

Models with a new architecture for on-device use: fast on a regular CPU and on phones. Versions for data extraction, RAG and tools, plus LFM2.5-VL for images and voice LFM2.5-Audio.

Developer
Liquid AI, USA
First release
Jul 2025
Latest release
Aug 2026
Sizes
230M – 24B-A2B
License
Commercial use with conditionsLFM Open License v1.0: free for companies with revenue up to 10 million dollars a year; above that, a separate license is required
Russian
Supported
Ready-made builds
GGUF, MLX (Apple)
Running
Available in OllamaAlso runs without a GPU
Industries
Documents and accounting, Customer support, Retail and marketplaces
Deploy on your server Hugging Face

What it does

  • Offline assistant on a laptop or phone
  • Data extraction from documents
  • Tool calling in apps
  • Knowledge-base search (RAG)

Where it is used

Mobile appsAutomotive and consumer electronicsSmall business

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. LFM2.5-VL-3B
  2. LFM2.5-2.6B
  3. LFM2.5-8B-A1B
  4. LFM2-24B-A2B
  5. LFM2.5-1.2B / VL-1.6B / Audio-1.5B
  6. LFM2-8B-A1B
  7. LFM2

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Liquid LFM be used in a commercial project?

With conditions. License: LFM Open License v1.0: free for companies with revenue up to 10 million dollars a year; above that, a separate license is required. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Liquid LFM need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Liquid LFM support Russian?

Yes, Russian is listed on the model card.

Where can I download Liquid LFM and what does it cost?

The Liquid LFM weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextSmolLMHugging Face · USACommercial use allowed

Tiny open Hugging Face models for phones and laptops. SmolLM3 (3B) can reason and handle long context; the full training recipe is open.

DetailsTextPhiMicrosoft · USACommercial use allowed

Small Microsoft models trained on carefully selected data: strong at logic and math for their modest size. Versions with images and speech are available.

DetailsTextFalconTechnology Innovation Institute (TII) · UAECommercial use with conditions

A family from Abu Dhabi: from the early Falcon 40B and 180B to hybrid Falcon-H1 and tiny Falcon-H1-Tiny models of 90–600M parameters for devices.

Details

Source: huggingface.co/LiquidAI/LFM2.5-2.6B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.