Image-Text-to-Text
MLX
Safetensors
mistral3
mistral-common
ministral
ministral-3
vision-language
multimodal
quantized
edge
6-bit
base-model
Instructions to use mlx-community/Ministral-3-8B-Base-2512-6bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Ministral-3-8B-Base-2512-6bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("mlx-community/Ministral-3-8B-Base-2512-6bit") config = load_config("mlx-community/Ministral-3-8B-Base-2512-6bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Xet hash:
- 3d5a2c00d9704b4e61e4e33469c2be19785f0c01c704aa1bffa3344d6bde2321
- Size of remote file:
- 5.37 GB
- SHA256:
- f428913c8913234701dcba4b476498403b4c5992a046f6c9cfc15d04e44cfa25
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.