LFM2.5-24B-A2B
Liquid’s largest LFM: a 24B MoE reasoning model with about 2.45B active parameters.
LFM2.5-24B-A2B is Liquid AI’s largest LFM, a mixture of experts with 24B total and about 2.45B active parameters. It reasons on every request and is aimed at agents that call tools; weights are on Hugging Face.
- Provider
- Liquid AI
- Type
- Language model
- Released
- Oct 13, 2026
- Input
- text
- Output
- text
- Open weights
- Yes
Best for
- Agents
- Reasoning
- High volume / low cost
Strengths
- ≈2.45B active parameters
- Open weights
- Built for tool calling
More from Liquid AI
- LFM2.5-2.6B — Liquid AI. Compact on-device reasoning model on Liquid’s hybrid architecture.
- d1-3B — Liquid AI. Liquid’s open 3B decision model, fast enough for robots and edge devices.
- LFM2.5-Embedding-350M — Liquid AI. Tiny open embedding model for on-device semantic search.