LiquidAI has released LFM2.5-VL-3B, a vision-language model designed for edge devices. This new model offers significant improvements in screen understanding, object grounding, multi-image reasoning, and function calling. Trained on a massive dataset with enhanced vision data, LFM2.5-VL-3B demonstrates strong performance on various vision and text benchmarks, leading its size class in real-world image tasks and matching models like Gemma-4-E2B and Qwen3.5-2B in tool use. The model is optimized for efficient inference on both CPUs and GPUs, capable of running on-device with notable speed. AI
IMPACT Enhances on-device AI capabilities, particularly for vision tasks, potentially accelerating adoption in edge computing applications.
RANK_REASON New model release from a known AI lab (LiquidAI/Hugging Face). [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
