Welcome to the GGUF repository for NVIDIA's Nemotron-3-Embed-8B-BF16.

This model is a state-of-the-art, 8-billion parameter multilingual text embedding model optimized for Retrieval-Augmented Generation (RAG), semantic search, and cross-lingual retrieval workflows. It achieved #1 on the multilingual RTEB leaderboard (as of July 2026).

By converting the model to GGUF (GPT-Generated Unified Format), you can run enterprise-grade retrieval locally on consumer hardware (CPUs and GPUs) using tools like llama.cpp, Ollama, or LM Studio.

Below is the directory structure of the available .gguf files in this repository. Choose the quantization level that best fits your VRAM/RAM constraints!