---
license: apple-amlr
library_name: mlx
pipeline_tag: image-text-to-text
base_model: apple/FastVLM-7B
base_model_relation: quantized
tags:
- fastvlm
- mlx
- mlx-vlm
- safetensors
- transformers
- llava_qwen2
- image-text-to-text
- text-generation
- conversational
- custom_code
- vision-language
- multimodal
- apple-silicon
- quantized
- 7B
- q4 / 4-bit quantized
- 4-bit
- 4-bit precision
- q4
---

# fastvlm-7b-mlx-q4

This repository contains an MLX-converted FastVLM checkpoint.

## Model

- Base model: `apple/FastVLM-7B`
- Parameters: `7B`
- Precision: `q4 / 4-bit quantized`
- Approx. folder size: `4.9G`

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-7b-mlx-q4 --local-dir ./fastvlm-7b-mlx-q4

python -m mlx_vlm.generate \
  --model ./fastvlm-7b-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-7b-mlx-q4 | 4.9G | 3.00s | 1.139s | 1.303s | 1.277s | 1.239s |

## 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.