Picture published by the creator on Hugging Face.
LFM3-1.7B: Run local chat and tool-calling agents (1.73B)
Added · Updated
Made by Liquid AI
View profile on Hugging Face (opens in a new tab)Chat with a small text model that can call tools and give structured answers, for developers building local agents or specialized apps.
Model details
Original model LiquidAI/LFM3-1.7B
Input Text Output Text
Ways to use it Run locally
Role in this family: Fine-tuned version.
LiquidAI/LFM3-1.7B-Base (opens in a new tab)What it does
LFM3-1.7B is a text-only language model, already post-trained, built from short convolution and attention layers. It supports a 256K-token context window and can ask your app to run functions you describe, then use the results in its answer.
How to use it
For local use, download the GGUF version and open it in LM Studio, Ollama or llama.cpp, which run on CPUs and GPUs. Other checkpoints suit Transformers, vLLM, SGLang, MLX for Apple Silicon, or ONNX Runtime. Format chat messages with the chat template.
Common use cases
- Describe a function, such as a lookup your app can run, then ask a question that needs it. The model replies asking to call it; your app runs it and sends back the result.
- Ask it to answer in a set format your program can read, instead of free-form chat text.
Can I use this?
Requirements Choose the checkpoint that matches your runtime from the model page. Downloads are not gated.
Caveat Reasoning is on by default, and turning off thinking traces can be inconsistent, especially for reasoning-heavy tasks.
Worth knowing Not recommended for agentic coding or complex multi-step reasoning because of its small size. Use retrieval or search for knowledge-heavy tasks. Licensed under the LFM Open License v1.0; the model card does not summarize its terms.
Why it's here
- 1,550 people have liked it on Hugging Face.
- It was downloaded 73,562 times in the last 30 days.
Numbers as of 8 November 2026, from BuildTube’s latest daily refresh.
Behind it
View model pageBuildTube has not run or verified this project. Everything above is written from what the creator published.
Made this?
Quick questions
- What is LFM3-1.7B?
- LFM3-1.7B is a text-only language model, already post-trained, built from short convolution and attention layers.
- What can I use LFM3-1.7B for?
- Describe a function, such as a lookup your app can run, then ask a question that needs it. The model replies asking to call it; your app runs it and sends back the result; Ask it to answer in a set format your program can read, instead of free-form chat text
- Can I run LFM3-1.7B on my computer?
- It runs on your own hardware with a model runtime. The model card mentions Transformers, vLLM, SGLang; check its setup and hardware notes.
- What do I need to use LFM3-1.7B?
- Load the weights with Transformers, vLLM, SGLang, llama.cpp, Ollama, LM Studio, MLX or ONNX Runtime. About 1 GB of memory at 4-bit precision; other hardware needs are not documented.
- What license does LFM3-1.7B use?
- Licensed under the LFM Open License v1.0; the model card does not summarize its terms.
More from this week
- P-H3-Image-Comfy Make and edit 8-megapixel images in ComfyUI
Turn short text requests into 8-megapixel images and edit pictures on your own graphics card.
- Idol Turn one picture of an object into a 3D Gaussian splat
Idol turns one photo, render or generated image of an object into a 3D Gaussian splat file.
- agent-desktop Let AI agents read and click desktop apps
For developers building computer-use agents: agent-desktop lets an AI agent read and operate desktop apps on Mac, Windows or Linux from a command line.
Explore by topic
Post this
Download share imageFor makers
Made this? Show it’s on BuildTube — add the badge to your README or embed the card on your site.
README badge (Markdown)
[](https://buildtube.app/p/hf-liquidai-lfm3-1-7b/)Embed card (HTML)
<iframe src="https://buildtube.app/embed/hf-liquidai-lfm3-1-7b/" width="560" height="240" style="border:0;max-width:100%" loading="lazy" title="LFM3-1.7B on BuildTube"></iframe>