Modelpublic

numen-tech/Llama-3.3-70B-Instruct-w3a16g40sym

sourceHugging Facellama3.3updated 2y agoView on Hugging Face

0likes

Model Card

3-bit OmniQuant quantized version of Llama-3.3-70B-Instruct for inference with the Private LLM app.