LFM2.5-2.6B
Compact on-device reasoning model on Liquid’s hybrid architecture.
LFM2.5-2.6B is a compact reasoning model from Liquid AI, suited to agent workflows, data extraction, RAG and long-context processing on edge devices. Liquid advises against using it for agentic coding.
- Provider
- Liquid AI
- Type
- Language model
- Released
- Aug 11, 2026
- Context window
- 66K tokens
- Max output
- 8K tokens
- Price
- Free
- Input
- text
- Output
- text
- Open weights
- Yes
Best for
- Local & on-device
- Extraction & classification
- Agents
- High volume / low cost
Strengths
- 2.6B parameters
- Open weights
- Free tier on OpenRouter
More from Liquid AI
- LFM2.5-Embedding-350M — Liquid AI. Tiny open embedding model for on-device semantic search.