Run and interact with large language models using MLX framework
Run LLMs with MLX
mlx-lm$ mlx-lm generate --prompt 'Hello, how are you?'$ mlx-lm generate --model mlx-community/Mistral-7B-Instruct-v0.1-4bit --prompt 'Explain quantum computing'$ mlx-lm chat --model mlx-community/Llama-2-7b-chat-4bit