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.
spaces 10
Running
15
LFM2 MoE WebGPU
💧
WebGPU-accelerated Mixture of Experts
Running
Featured
87
LFM2 WebGPU – In-browser tool calling
🛠
In-browser tool calling, powered by Transformers.js
Running
11
LFM2.5-Audio WebGPU Demo
🎙
ASR, TTS & conversational audio in your browser
Running
Featured
40
LFM2 VL WebGPU
📹
Real-time video captioning in your browser
Build error
Featured
36
LFM2 MCP
🚀
In-browser tool calling with MCP, powered by Transformers.js
Running
36
Wllama
🦙
Run GGUF directly on your browser!
models 84
LiquidAI/LFM2-24B-A2B-ONNX
Text Generation • Updated • 403 • 7
LiquidAI/LFM2.5-VL-1.6B
Image-Text-to-Text • 2B • Updated • 117k • 258
LiquidAI/LFM2-8B-A1B-ONNX
Text Generation • Updated • 320 • 4
LiquidAI/LeapBundles
Updated • 14
LiquidAI/LFM2-VL-450M-GGUF
Image-Text-to-Text • 0.4B • Updated • 86.2k • 38
LiquidAI/LFM2-8B-A1B
Text Generation • 8B • Updated • 65.1k • 340
LiquidAI/LFM2-24B-A2B
Text Generation • 24B • Updated • 39.4k • 295
LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16
Text Generation • 1B • Updated • 319 • 3
LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit
Text Generation • 0.3B • Updated • 4.26k • 7
LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit
Text Generation • 0.2B • Updated • 100