LFM3-1.7B
A small model from Liquid AI, free to download and light enough for a phone or laptop, made for building AI agents that use tools and produce structured answers.
trckr found this on Nov 7, 10 days after it came out, so it sent no alert. Its release date comes from Hugging Face.
Key facts
- Released
- Oct 27, 2026
- What it does
- Text and chat: Writes, answers questions and holds a conversation.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.
Can I use it?
In an app
No app mentioned so far.
For developers
Developers can use it now through an API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet..
Download
Free to download and run on your own computer: it has Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open"..
Price and limits
What developers pay to use it through the API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet., per million Tokens: The small chunks of text a model reads and writes, about three-quarters of a word each. Prices and limits are counted in tokens. sent (input) or written back (output), and how much it can take in at once.
- Input
- $0.08
- per million tokensCached: $0.02
- Output
- $0.20
- per million tokens
- Context window: How much a model can keep in mind at once: your question, any files you share and its own replies. Measured in tokens; 1,000 tokens is about 750 words.
- 262K tokens
- about 200,000 words
View moreView less
- Longest answer
- 8K tokens (about 6,100 words)
From OpenRouter, checked .
How it scores
Not in the independent rankings yet. New models usually show up within a few weeks, and this page updates when they do.
Compare LFM3-1.7B with
It came out 77 days after LFM2.5-2.6B, the lab's previous model.
The details
A 1.7 billion parameters: Small enough to run on a phone or laptop. Parameters are the numbers a model learns: a rough measure of its size. Post-training: The finishing stage after the main training, where a model learns to follow instructions, use tools, be helpful and avoid harm. text model from Liquid AI, built for local Agent: An AI that doesn't just answer but takes steps on its own to finish a task: searching the web, running code or using apps., Tool use: A model's ability to use other software, like a calculator, a web search or a booking system, instead of only writing text. and structured outputs, with a A 256K-token context window: It can keep about 190,000 words, or 640 book pages in mind at once: the question, any files you share, and its own replies. and built-in Reasoning model: A model that thinks step by step before answering. Slower, but much better at maths, code and tricky questions.. Released as free-to-download weights under the LFM Open License v1.0, with a base variant and Quantisation: Shrinking a model by storing its numbers less precisely, so it fits on smaller computers. A little less accurate, much lighter. FP8, GGUF, AWQ and MLX are common formats. Checkpoint: A saved copy of a model at one point in its training. Labs share checkpoints for researchers; they're rarely finished products. for common local runtimes.
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
liquid/lfm-3-1.7bLiquidAI/LFM3-1.7BLiquidAI/LFM3-1.7B-BaseLiquidAI/LFM3-1.7B-FP8LiquidAI/LFM3-1.7B-GGUFLiquidAI/LFM3-1.7B-ONNXLiquidAI/LFM3-1.7B-NVFP4Timeline
/OpenRouterFirst signal
Get alerts like this the moment they happen.
From Liquid AI and every other major lab.