# Low-Memory Inference

This is the FP8 static quantization version of OpenGVLab/InternVL3-38B, optimized for high-performance inference using vLLM. It achieves approximately 2x acceleration on vision-language tasks with minimal accuracy loss.

NLLB-200 Distilled 1.3B is a neural machine translation model developed by Meta, supporting translation between 200 languages, utilizing CTranslate2 for efficient inference.