| base_model: | |
| - nvidia/Mistral-NeMo-Minitron-8B-Base | |
| library_name: transformers | |
| license: other | |
| license_name: nvidia-community-model-license | |
| license_link: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/ | |
| tags: | |
| - mlx | |
| # mlx-community/Mistral-NeMo-Minitron-8B-Instruct-4bit | |
| The Model [mlx-community/Mistral-NeMo-Minitron-8B-Instruct-4bit](https://huggingface.co/mlx-community/Mistral-NeMo-Minitron-8B-Instruct-4bit) was converted to MLX format from [nvidia/Mistral-NeMo-Minitron-8B-Instruct](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Instruct) using mlx-lm version **0.17.1**. | |
| ## Use with mlx | |
| ```bash | |
| pip install mlx-lm | |
| ``` | |
| ```python | |
| from mlx_lm import load, generate | |
| model, tokenizer = load("mlx-community/Mistral-NeMo-Minitron-8B-Instruct-4bit") | |
| response = generate(model, tokenizer, prompt="hello", verbose=True) | |
| ``` | |