Liquid AI LFM2.5 VL

LFM2.5 VL 3B is a compact multimodal language model designed for efficient on-device vision-language tasks, combining the LFM2.5-2.6B language model with a SigLIP2 NaFlex vision encoder. It uses a 30-layer hybrid architecture with 2,048 hidden size, 32 attention heads, and 8 key-value heads, alternating short convolution and full-attention layers for efficient sequence processing. Supporting a 32K-token context window, it uses native-resolution image processing with 512×512 patches and thumbnail processing. The model is optimized for image grounding, object detection, full-page OCR, layout understanding, multilingual applications, and efficient on-device multimodal inference.

LFM2.5 VL 1.6B is a compact multimodal language model designed for efficient on-device vision-language tasks, combining the LFM2.5-1.2B language model with a SigLIP2 NaFlex 400M vision encoder. It uses a 16-layer hybrid architecture with 2,048 hidden size, 32 attention heads, and 8 key-value heads, alternating convolution and full-attention layers for efficient sequence processing. Supporting a 32K-token context window, it uses native-resolution image processing with 512×512 patches and thumbnail processing. The model is optimized for image understanding, OCR, multi-image processing, multilingual applications, and efficient on-device multimodal inference.

LFM2.5 VL 450M is a compact vision-language model designed for efficient multimodal understanding and on-device deployment, combining the LFM2.5-350M language model with an 86M SigLIP2 NaFlex vision encoder. It uses a 16-layer hybrid architecture with 1,024 hidden size, 16 attention heads, and 8 key-value heads, alternating short convolution and full-attention layers for efficient sequence processing. Supporting a 32K-token context window, it processes native-resolution images through 512×512 tiling and thumbnail encoding. The model is optimized for multilingual vision understanding, object detection, bounding box prediction, instruction following, and function calling.