# LFM2-24B-A2B

LFM2-24B-A2B is the largest model in the LFM2 family of hybrid architectures designed for efficient on-device deployment. Built as a 24B parameter Mixture-of-Experts model with only 2B active parameters per token, it delivers high-quality generation while maintaining low inference costs. The model fits within 32 GB of RAM, making it practical to run on consumer laptops and desktops without sacrificing capability.

## Model Information

- **Organization**: [Liquid AI](/llm.txt)
- **Slug**: lfm-2-24b-a2b
- **Available at Providers**: 7
- **Release Date**: February 25, 2026

## Providers

| Provider | Name | $ Input (per 1M) | $ Output (per 1M) | Free | Link |
|----------|------|-----------------|------------------|------|------|
| [Kilo Code](/llm/kilocode.txt) | LiquidAI: LFM2-24B-A2B | 0.03 | 0.12 |  | [View](https://kilo.ai/models/liquid/lfm-2-24b-a2b) |
| [OpenRouter](/llm/openrouter.txt) | LFM2-24B-A2B | 0.03 | 0.12 |  | [View](https://openrouter.ai/liquid/lfm-2-24b-a2b-20260224) |
| [Together AI](/llm/togetherai.txt) | LFM2-24B-A2B | 0.03 | 0.12 |  |  |
| [Yupp](/llm/yupp.txt) | LFM2 24B A2B Preview (Together AI) |  |  |  |  |
| [Nano-GPT](/llm/nanogpt.txt) | LFM2 24B A2B |  |  |  |  |
| [Writingmate](/llm/writingmate.txt) | LiquidAI: LFM2-24B-A2B |  |  |  | [View](https://writingmate.ai/models/liquid/lfm-2-24b-a2b) |
| [Yupp](/llm/yupp.txt) | LFM2-24B-A2B (OpenRouter) |  |  |  |  |

---

[← Back to all providers](/llm.txt)