LFM2 is a new generation of hybrid models, designed for on-device deployment.
AI & ML interests
A new generation of foundation models from first principles.
Recent Activity
View all activity
spaces 9
Running
5
LFM2 VL WebGPU
📹
Real-time video captioning in your browser
Running
8
LFM2.5-Audio WebGPU Demo
🎙
ASR, TTS & conversational audio in your browser
Build error
Featured
36
LFM2 MCP
🚀
In-browser tool calling with MCP, powered by Transformers.js
Running
35
Wllama
🦙
Run GGUF directly on your browser!
Running
Featured
84
LFM2 WebGPU – In-browser tool calling
🛠
In-browser tool calling, powered by Transformers.js
Running
Featured
89
LFM2.5 1.2B Thinking WebGPU
💧
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
models 84
LiquidAI/LFM2-8B-A1B
Text Generation • 8B • Updated
• 63.9k • 333
LiquidAI/LFM2-24B-A2B
Text Generation • 24B • Updated
• 25.9k • 283
LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16
Text Generation • 1B • Updated
• 326 • 3
LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit
Text Generation • 0.3B • Updated
• 2.51k • 7
LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit
Text Generation • 0.2B • Updated
• 92
LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit
Text Generation • 0.3B • Updated
• 48
LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit
Text Generation • 0.2B • Updated
• 469 • 5
LiquidAI/LFM2-24B-A2B-ONNX
Text Generation • Updated
• 68 • 6
LiquidAI/LFM2-24B-A2B-MLX-bf16
Text Generation • 24B • Updated
• 137 • 2
LiquidAI/LFM2-24B-A2B-MLX-6bit
Text Generation • 24B • Updated
• 117 • 4