README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - llava
  - multimodal
  - qwen
  - mlx
  - mlx

mlx-community/nanoLLaVA-1.5-4bit

This model was converted to MLX format from mlx-community/nanoLLaVA-1.5-bf16 using mlx-vlm version 0.1.6. Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model mlx-community/nanoLLaVA-1.5-4bit --max-tokens 100 --temp 0.0