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 7
pinned
Configuration error
Featured
36
LFM2 MCP
🚀
In-browser tool calling with MCP, powered by Transformers.js
pinned
Running
Featured
80
LFM2 WebGPU – In-browser tool calling
🛠
In-browser tool calling, powered by Transformers.js
pinned
Running
32
Wllama
🦙
Run GGUF directly on your browser!
Running
37
LFM2.5 1.2B Thinking WebGPU
💧
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Running
4
LFM2.5-Audio WebGPU Demo
🎙
ASR, TTS & conversational audio in your browser
Running
Featured
70
LFM2.5-VL-1.6B WebGPU
🧠
In-browser vision-language inference with LFM2.5-VL-1.6B
models 84
LiquidAI/LFM2-8B-A1B
Text Generation • 8B • Updated
• 25.2k • 320
LiquidAI/LFM2-24B-A2B
Text Generation • 24B • Updated
• 3.08k • 164
LiquidAI/LFM2-24B-A2B-ONNX
Text Generation • Updated
• 19 • 6
LiquidAI/LFM2-24B-A2B-MLX-bf16
Text Generation • 24B • Updated
• 53 • 2
LiquidAI/LFM2-24B-A2B-MLX-6bit
Text Generation • 24B • Updated
• 28 • 2
LiquidAI/LFM2-24B-A2B-MLX-4bit
Text Generation • 24B • Updated
• 65 • 4
LiquidAI/LFM2-24B-A2B-MLX-8bit
Text Generation • 24B • Updated
• 67 • 6
LiquidAI/LFM2-24B-A2B-MLX-5bit
Text Generation • 24B • Updated
• 24 • 1
LiquidAI/LFM2.5-1.2B-Instruct
Text Generation • 1B • Updated
• 97.7k • 503
LiquidAI/LFM2.5-VL-1.6B
Image-Text-to-Text • 2B • Updated
• 141k • 239