# LFM2.5 350M

> Canonical: https://www.overmindlab.ai/models/lfm-2-5-350m

Compact on-device instruct — teacher for the 230M distill.

| Property | Value |
| --- | --- |
| Model ID | LiquidAI/LFM2.5-350M |
| Provider | Liquid AI |
| Group | LFM2.5 |
| Parameters | 350M |
| Tier | Compact |
| Context window | 32K |
| Max training context | 32K |
| Tool calling | Yes |
| Training methods | — |
| Training cost | from $0.50 |
| Serving cost (per 1M output tokens) | from $2.50 |

## Overview

LFM2.5-350M is the compact instruct hybrid used as the distillation teacher for 230M. Same edge-first architecture with stronger out-of-the-box tool use and multilingual coverage.

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

## Good for

- Edge agent prototypes with a bit more headroom than 230M
- Multilingual tool-calling at sub-1B cost
- Domain LoRA when 230M underfits

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

## Related models

- [LFM2.5 1.2B Instruct](https://www.overmindlab.ai/models/lfm-2-5-1-2b-instruct): 1.2B, 32K context
- [LFM2.5 230M](https://www.overmindlab.ai/models/lfm-2-5-230m): 230M, 32K context