# LFM3 1.7B

> Canonical: https://www.overmindlab.ai/models/lfm-3-1-7b

1.7B agent model with a 256K window and tool calling.

| Property | Value |
| --- | --- |
| Model ID | LiquidAI/LFM3-1.7B |
| Provider | Liquid AI |
| Group | LFM3 |
| Parameters | 1.7B |
| Tier | Compact |
| Context window | 256K |
| Max training context | 128K |
| Tool calling | Yes |
| Training methods | LoRA · Full |
| Training cost | from $0.55 |
| Serving cost (per 1M output tokens) | from $2.50 |

## Overview

LFM3-1.7B is Liquid's text instruct checkpoint: 24 tri-hybrid layers, tool calling, and a 256K window. Thinking is off when enable_thinking is false.

Liquid AI hybrid models for on-device and edge deployment. Fast decode, low memory, and agentic post-training across the ladder.

## Good for

- Tool-calling and agent loops at compact size
- Instruction following on a 256K window
- Domain LoRA on a single GPU

Train this model on your agent's data: https://docs.overmindlab.ai/models/training.md