LFM2.5-VL-3B

LFM2.5-VL-3B is a 3.1-billion-parameter vision-language model designed for high-performance, on-device inference. It features significant improvements in screen understanding, grounding, and function calling, allowing it to outperform larger models while maintaining low latency on edge hardware.

LFM2.5-VL-3B is a 3.1-billion-parameter vision-language model designed for high-performance, on-device inference. It features significant improvements in screen understanding, grounding, and function calling, allowing it to outperform larger models while maintaining low latency on edge hardware.

• 01Advanced screen and UI understanding for mobile, web, and desktop
• 02Enhanced function calling and tool-use capabilities
• 03Improved grounding performance with high-precision bounding box detection
• 04Multi-image input reasoning support
• 05Optimized for edge inference with support for llama.cpp, MLX, and vLLM
• 06Non-reasoning architecture for low-latency, direct responses