# LiquidAI/LFM2-8B-A1B

LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.

## Model Information

- **Organization**: [Liquid AI](/llm.txt)
- **Slug**: lfm2-8b-a1b
- **Available at Providers**: 8
- **Release Date**: October 20, 2025

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [OpenRouter](/llm/openrouter.txt) | LFM2-8B-A1B | 0.01 | 0.02 |  | [View](https://openrouter.ai/liquid/lfm2-8b-a1b) |
| [ValorGPT](/llm/valorgpt.txt) | LI |  |  |  | [View](https://www.valorgpt.com/models/liquid-lfm2-8b-a1b) |
| [Yupp](/llm/yupp.txt) | LiquidAI LFM2-8B-A1B (OpenRouter) |  |  |  |  |
| [LangDB](/llm/langdb.txt) | lfm2-8b-a1b |  |  |  | [View](https://langdb.ai/app/models) |
| [Kilo Code](/llm/kilocode.txt) | LiquidAI: LFM2-8B-A1B | 0.01 | 0.02 |  | [View](https://kilo.ai/models/liquid/lfm2-8b-a1b) |
| [Blackbox AI](/llm/blackboxai.txt) | blackboxai/liquid/lfm2-8b-a1b |  |  |  |  |
| [WaveSpeed AI](/llm/wavespeed.txt) | lfm2-8b-a1b | 0.01 | 0.02 |  |  |
| [Writingmate](/llm/writingmate.txt) | LiquidAI: LFM2-8B-A1B |  |  |  | [View](https://writingmate.ai/models/liquid/lfm2-8b-a1b) |

---

[← Back to all providers](/llm.txt)