# Lightweight large model

A.X 4.0 Light is a lightweight large language model developed by SKT AI Model Lab, built on Qwen2.5 and optimized for Korean understanding and enterprise deployment.

Molmo-7B-D is a large language model quantized with BnB 4-bit. The model size is reduced from 30GB to 7GB, and the video memory requirement is reduced to about 12GB.

Phi-3 4k Instruct is a lightweight yet powerful language model, processed with 4-bit quantization to reduce resource requirements.

The GGUF quantized version of the Llama 3 8B instruction model, suitable for local inference and supporting efficient deployment

MiniCPM is an edge-side large language model jointly developed by FaceWall Intelligence and Tsinghua University's Natural Language Processing Lab, with only 2.4 billion non-word embedding parameters (2.4B) and supports a 128k context window.

MobileVLM is a fast and powerful multi-modal vision-language model designed specifically for mobile devices, supporting efficient cross-modal interaction.

Open-source Chinese conversational large language model optimized with instruction fine-tuning, specializing in Chinese cultural tasks, with 1.4B/2.6B parameters