LFM2 VL 3B
LFM2-VL-3B is a 3B vision-language model that reads images with text and answers in natural language or structured JSON. It handles OCR, charts, tables, and screenshots with long context and low-latency streaming, making it practical for multimodal RAG and assistants.
- Type
- Text
- Weights
- Open
- Downloads
- 29k
- Likes
- 208
- Pipeline
- image text to text
- License
- other
Model hub
LiquidAI/LFM2.5-VL-3B
- Repo
- LiquidAI/LFM2.5-VL-3B
- Library
- transformers
- Access
- Public
Technical tags and languages
More from Liquid AI
13
-
15k DL
LFM 2.5 1.2B JP 202606
Text
LFM2.5-1.2B-JP-202606 is Liquid AI’s 1.17B Japanese-focused text model for chat, instruction following, math,…
-
3.8k DL
LFM2 24B A2B
Text
LFM2-24B-A2B is a hybrid Mixture-of-Experts language model designed for efficient on-device deployment, scali…
-
328 DL
LFM2-Audio-1.5
Multimodal
LFM2-Audio-1.5 is a unified audio foundation model for real-time speech, music, and sound effects. It transcr…
-
112k DL
LFM2.5 1.2B
Text
LFM2.5-1.2B is Liquid AI’s 1.2B hybrid edge model for on-device chat and tools, trained on 28T tokens and RL,…
-
9.7k DL
LFM2.5 1.2B Thinking
Text
LFM2.5-1.2B-Thinking is Liquid AI’s 1.2B parameter reasoning-focused variant of its LFM2.5 edge family, optim…
-
83k DL
LFM2.5 230M
Text
LFM2.5-230M is a 230M-parameter lightweight language model built on the LFM2 architecture, designed for fast…
-
97k DL
LFM2.5 350M
Text
LFM2.5-350M is Liquid AI’s compact 350M-parameter language model optimized for fast inference, tool use, data…
-
4.7k DL
LFM2.5 ColBERT 350M
Text
350M-parameter bidirectional multilingual retrieval model using per-token ColBERT-style late interaction (Max…
About Liquid AI
1
Liquid AI is an MIT spin-off building efficient general-purpose AI models (Liquid Foundation Models, or LFMs) that run on edge devices with less memory and power. They recently raised $250M in Series A funding to scale model development and deployment.