17B open-weight LLM by mlx-community
Llama-4-Maverick-17B-16E-Instruct-4bit is an open-weight text-generation model with roughly 17B parameters published by mlx-community on the Hugging Face Hub. It has 321 downloads. Runs with mlx.
mlx-community
api
free
Others in the same category, ranked by how often they are opened.