Liquid AI’s LFM3 1.7B is a compact text model designed for local assistants and specialized tasks. Ollama lists different download sizes for its local backends.
Where it works well
- Small local download.
- Structured text and tool calling in compatible apps.
- Focused, specialized tasks.
Common use cases
- Turn short notes into a checklist.
- Extract fields from a supplied message.
- Try a simple local assistant workflow.
Know its limits
- It is text-only; use a vision model for images.
- Liquid does not recommend it for complex reasoning or agentic coding.
- Tool use requires a compatible configured app, and long context needs more memory.
Run it on your computer
Compatibility: Use a current runtime with LFM3 support.
Start with a compressed download and a short conversation. Our estimate is about 4 GB of total RAM or Mac unified memory, with room for the operating system. The listed 1.1–1.7 GB download is the model file, not its full running memory use.
Check the model’s supported runtime and hardware before loading it. System RAM on a PC and unified memory on a Mac are different from dedicated NVIDIA VRAM. A memory match doesn’t guarantee compatibility or speed. Choose a smaller model if responses are too slow.
Use a desktop app that supports the listed model format, such as LM Studio or Ollama. Download the exact local variant, load it in Chat, and start with one small task. Model downloads need internet; local chat can work offline once the model is downloaded.
Official model information
See the linked model sources for current capabilities. These use cases are practical starting suggestions, not performance guarantees.