Views
No views yet
| Quantization | affine, 8 bits, group size 64 (vision tower included) |
| On-disk size | ~9.5 GB |
| Peak memory | ~11 GB |
| Tokenizer | loaded from moondream/starmie-v1 at runtime (not bundled) |
1pip install mlx-vlm
2
3python -m mlx_vlm.generate \
4 --model beshkenadze/moondream3-preview-mlx-8bit \
5 --image path/to/image.jpg \
6 --prompt "Describe this image." \
7 --max-tokens 128 --temperature 0.0