Up to 3.2x Faster Inference with LFM2.5-DSpark
• 28
A new generation of foundation models from first principles.
Run LFM2.5-VL-3B locally in your browser with WebGPU
Run an on-device LFM2.5 research agent with WebGPU
Fix typos with a tiny local model on CPU
Multilingual PII detection with LFM2.5, server-side CPU
Masked diffusion with LFM2.5 Encoder on CPU
Policy linting with LFM2.5 Encoder on CPU