LFM2.5-Embedding-350M
Tiny open embedding model for on-device semantic search.
LFM2.5-Embedding-350M is a compact text embedding model from Liquid AI producing 1,024-dimension vectors for retrieval and semantic search; small enough to run on edge devices.
- Provider
- Liquid AI
- Type
- Embedding model
- Released
- Aug 18, 2026
- Context window
- 512 tokens
- Price
- Free tier on OpenRouter
- Input
- text
- Output
- embedding
- Open weights
- Yes
Best for
- Local & on-device
- High volume / low cost
Strengths
- 350M parameters
- Open weights
More from Liquid AI
- LFM2.5-2.6B — Liquid AI. Compact on-device reasoning model on Liquid’s hybrid architecture.