Models · MarkTechPost ·

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

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

Liquid AI released LFM2.5-230M, a 230M-parameter open-weight model for on-device inference. The company says it supports llama.cpp, MLX, vLLM, SGLang, and ONNX, and reports strong instruction-following and tool-use performance on mobile and edge devices.

Read the full story at MarkTechPost →