fastvlm-7b-mlx-fp16

fastvlm-7b-mlx-fp16

This repository contains an MLX-converted FastVLM checkpoint.

Model

• Base model: apple/FastVLM-7B
• Parameters: 7B
• Precision: fp16
• Approx. folder size: 15G

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

hf download dbaek111/fastvlm-7b-mlx-fp16 --local-dir ./fastvlm-7b-mlx-fp16

python -m mlx_vlm.generate \
  --model ./fastvlm-7b-mlx-fp16 \
  --image /path/to/your/image.jpg \
  --prompt "Explain the image." \
  --max-tokens 64 \
  --temp 0.0

Benchmark

Benchmarked on an Apple Silicon Mac with the patched FastVLM mlx-vlm workflow.

• Task: pedestrian wayfinding captioning
• Images: three local test images resized to 512px and 1024px long edge
• Prompt: Describe what is visible for pedestrian wayfinding in one short sentence. Do not list categories. Do not mention anything you cannot see. Keep under 30 words.
• Max tokens: 64
• Temperature: 0.0
• Timing: model loaded once per image set, then three images processed sequentially

Model Selection

Per-Image Timing

Each cell is img1 / img2 / img3 inference time in seconds.

Compatibility

This is an MLX export of FastVLM for Apple Silicon Macs. It includes the CoreML FastViTHD vision tower as fastvithd.mlpackage.

This repository is not a standard PyTorch Transformers checkpoint and is not intended for vLLM, SGLang, or Linux GPU inference.

Notes

This is an MLX-converted derivative of Apple FastVLM.

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