70B open-weight LLM by mlx-community
nvidia_Llama-3.1-Nemotron-70B-Instruct-HF_4bit is an open-weight text-generation model with roughly 70B parameters published by mlx-community on the Hugging Face Hub. It has 660 downloads. Runs with transformers.
mlx-community
api
free
Others in the same category, ranked by how often they are opened.
