Liquid AI: LiquidAI: 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... Hybrid architecture with 24B total / 2B active params Designed for efficient on-device deployment Very low pricing at $0.03/$0.12 MoE for scalable inference Very limited capabilities vs larger models Narrow use case for on-device/edge Small context window for its class On-device AI applications Ultra-low-cost inference Edge deployment scenarios
Specifications
| Lab | Liquid AI |
|---|---|
| Context window | 128,000 |
| Input price | $0.03/1M |
| Output price | $0.12/1M |
| Release | 2026-02-01 00:00:00 |
Strengths
- Hybrid architecture with 24B total / 2B active params
- Designed for efficient on-device deployment
- Very low pricing at $0.03/$0.12
- MoE for scalable inference
Weaknesses
- Very limited capabilities vs larger models
- Narrow use case for on-device/edge
- Small context window for its class
Best for
- On-device AI applications
- Ultra-low-cost inference
- Edge deployment scenarios
In Depth: LiquidAI: LFM2-24B-A2B
Summary
LiquidAI: LFM2-24B-A2B is an AI model from Liquid AI.
Released 2026-02-01 00:00:00. It currently appears in the Overall category on LMRank. It supports Text input and produces Text output, with a context window of 128K tokens. Input pricing is $0.03 per 1M tokens and output is $0.12 per 1M tokens on OpenRouter.