LFM2.5-Encoders for Fast Long-Context Inference on CPU
• 40
AI & ML interests
A new generation of foundation models from first principles.
Articles
Running
6
English spellchecker
✍
Fix typos with a tiny local model on CPU
Running
1
PII Detection
🕵
Multilingual PII detection with LFM2.5, server-side CPU
Running
4
Masked Diffusion
🌫
Masked diffusion with LFM2.5 Encoder on CPU
Running
6
Policy Linting
🖍
Policy linting with LFM2.5 Encoder on CPU
Running
9
Prompt Routing
🧭
Route prompts with LFM2.5 Encoder on CPU
Running
Featured
26
LFM2 ColBERT
🏆
One Model to Embed Them All
Running
Featured
91
LFM2 WebGPU – In-browser tool calling
🛠
In-browser tool calling, powered by Transformers.js
Running
16
LFM2.5-Audio WebGPU Demo
🎙
ASR, TTS & conversational audio in your browser
Running
Featured
39
LFM2 MCP
🚀
In-browser tool calling with MCP, powered by Transformers.js
Running
Featured
29
ColBERT Tool Selection
🧭
Send a request, the retriever pre-selects the right tools
Running on Zero
Agents
Featured
44
LFM2.5 8B A1B
🌖
Chat with an AI assistant using the LFM2.5 model
Running
Featured
60
LFM2.5-VL-450M WebGPU
📹
Live video captioning and object tracking in your browser
Running
Featured
47
LFM2 MoE WebGPU
💧
WebGPU-accelerated Mixture of Experts
Running
Featured
66
LFM2 VL WebGPU
📹
Real-time video captioning in your browser
Running
39
Wllama
🦙
Run GGUF directly on your browser!
Running
Featured
123
LFM2.5 1.2B Thinking WebGPU
💧
Run LFM2.5-1.2B-Thinking directly in your browser on WebGPU
Running
4
LFM2-VL-450M WebGPU
⚡
In-browser vision-language inference with LFM2-VL-450M
Running
Featured
92
LFM2.5-VL-1.6B WebGPU
🧠
In-browser vision-language inference with LFM2.5-VL-1.6B