Liquid AI Ships LFM2.5-230M with llama.cpp, MLX, vLLM, SGLang, and ONNX Support for On-Device Inference

Liquid AI has released the LFM2.5-230M, a compact open-weight model designed for efficient on-device tasks such as data extraction and tool use. By supporting major inference frameworks like llama.cpp and ONNX, the model achieves high performance on hardware ranging from smartphones to single-board computers, outperforming several larger competitors in efficiency.