LFM2-VL is our first series of vision-language models, designed for on-device deployment.
AI & ML interests
A new generation of foundation models from first principles.
Recent Activity
spaces
4
pinned
Running
33
LFM2 MCP
🚀
In-browser tool calling with MCP, powered by Transformers.js
pinned
Running
67
LFM2 WebGPU – In-browser tool calling
🛠
In-browser tool calling, powered by Transformers.js
pinned
Running
25
Wllama
🦙
Run GGUF directly on your browser!
Running
6
LFM2 ColBERT
🏆
One Model to Embed Them All
models
33
LiquidAI/LFM2-ColBERT-350M
Sentence Similarity
•
0.4B
•
Updated
•
27
LiquidAI/LFM2-350M
Text Generation
•
0.4B
•
Updated
•
25.1k
•
163
LiquidAI/LFM2-700M
Text Generation
•
0.7B
•
Updated
•
9.33k
•
83
LiquidAI/LFM2-2.6B
Text Generation
•
3B
•
Updated
•
57k
•
139
LiquidAI/LFM2-8B-A1B
Text Generation
•
8B
•
Updated
•
11.8k
•
224
LiquidAI/LFM2-1.2B
Text Generation
•
1B
•
Updated
•
514k
•
318
LiquidAI/LFM2-350M-PII-Extract-JP
Text Generation
•
0.4B
•
Updated
•
426
•
39
LiquidAI/LFM2-VL-450M
Image-Text-to-Text
•
0.5B
•
Updated
•
10.8k
•
128
LiquidAI/LFM2-VL-3B
Image-Text-to-Text
•
3B
•
Updated
•
1.31k
•
68
LiquidAI/LFM2-VL-1.6B
Image-Text-to-Text
•
2B
•
Updated
•
7.24k
•
201
datasets
0
None public yet