---
license: apple-amlr
library_name: mlx-vlm
base_model: apple/FastVLM-0.5B
tags:
- fastvlm
- mlx
- mlx-vlm
- vlm
- quantized
- apple-silicon
- 0.5B
- q4 / 4-bit quantized
---

# fastvlm-0.5b-mlx-q4

This repository contains an MLX-converted FastVLM checkpoint.

## Model

- Base model: `apple/FastVLM-0.5B`
- Parameters: `0.5B`
- Precision: `q4 / 4-bit quantized`
- Approx. folder size: `819M`

The checkpoint was converted from Apple FastVLM using the official FastVLM model export workflow and patched `mlx-vlm`.

## Files

This repository should include:

- `config.json`
- MLX model weights
- tokenizer files
- `fastvithd.mlpackage` vision tower

## Example Usage

```bash
hf download dbaek111/fastvlm-0.5b-mlx-q4 --local-dir ./fastvlm-0.5b-mlx-q4

python -m mlx_vlm.generate \
  --model ./fastvlm-0.5b-mlx-q4 \
  --image /path/to/your/image.jpg \
  --prompt "Explain the image." \
  --max-tokens 64 \
  --temp 0.0
```

## Benchmark

Benchmark condition:

- Images: three 512px test images
- Max tokens: `64`
- Temperature: `0.0`
- Same prompt across all tested variants
- Model loaded once, then images processed sequentially

| Model | Size | Load | Img1 | Img2 | Img3 | Avg |
|---|---:|---:|---:|---:|---:|---:|
| fastvlm-0.5b-mlx-q4 | 819M | 2.85s | 0.299s | 0.351s | 0.338s | 0.330s |

## Notes

This is a converted and quantized derivative of Apple FastVLM.

Please refer to the original Apple FastVLM repository and model card for license and usage conditions.