Specifications
| Property | Value |
|---|---|
| Parameters | 450M |
| Context Length | 32K tokens |
| Architecture | LFM2-VL (Dense) |
Ultra-Light
Minimal memory footprint
Low Latency
Fastest vision model inference
Edge-Ready
Runs on mobile and embedded devices
Quick Start
- Transformers
- vLLM
- SGLang
- llama.cpp