moondream3-preview-mlx-4bit
A 4-bit MLX quantization of moondream/moondream3-preview for running on Apple Silicon with mlx-vlm.
| Quantization | affine, 4 bits, group size 64 (vision tower included) |
| On-disk size | ~5 GB |
| Peak memory | ~6.5 GB |
| Tokenizer | loaded from moondream/starmie-v1 at runtime (not bundled) |
Usage
pip install mlx-vlm
python -m mlx_vlm.generate \
--model beshkenadze/moondream3-preview-mlx-4bit \
--image path/to/image.jpg \
--prompt "Describe this image." \
--max-tokens 128 --temperature 0.0
License
moondream3 is released under the Business Source License 1.1 (BSL 1.1) — see LICENSE.md. This quantization is a derivative redistribution under the same terms.
- Downloads last month
- 205
Model size
2B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for beshkenadze/moondream3-preview-mlx-4bit
Base model
moondream/moondream3-preview
# 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("beshkenadze/moondream3-preview-mlx-4bit") config = load_config("beshkenadze/moondream3-preview-mlx-4bit") # 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)