Run FastVLM on Mac

FASTVLM GUIDE · Apple Silicon

Choose between the official MLX demo workflow and exported Apple Silicon model resources.

All FastVLM guides

Before you run

The official app requires macOS 15.2+ or iOS 18.2+ and a compatible Xcode toolchain. Download the model before building. Use an empty model folder for the initial download; keep any existing custom model elsewhere before changing variants.

Check your first result

Build and run in Xcode. Select the target device, configure signing for iPhone, then ask a question about an image or camera frame. Check the generated answer and the app’s TTFT display.

Stage2 / Stage3 and Apple Silicon files →

Source checked September 12, 2026. Runtime performance depends on your device.

Step by step

1. Confirm your Mac uses Apple Silicon.
2. Clone the official repository and inspect the app directory.
3. Download the documented MLX-compatible model assets.
4. Start with 0.5B before moving to a larger model.

Example

Apple Silicon

git clone https://github.com/apple-aiml-research/ml-fastvlm.git
cd ml-fastvlm
chmod +x app/get_pretrained_mlx_model.sh
app/get_pretrained_mlx_model.sh --model 0.5b --dest app/FastVLM/model
open app/FastVLM/FastVLM.xcodeproj

Verify against the primary source

APIs, model files and dependency versions can change. Treat this page as an implementation map, then confirm the current command and license in the linked official documentation.

Open official source

FastVLM with MLX

FASTVLM GUIDE · MLX

Use the MLX-based app and official Apple Silicon checkpoints for native experiments on Mac and iOS.

All FastVLM guides

Before you run

The official app requires macOS 15.2+ or iOS 18.2+ and a compatible Xcode toolchain. Download the model before building. Use an empty model folder for the initial download; keep any existing custom model elsewhere before changing variants.

Check your first result

Build and run in Xcode. Select the target device, configure signing for iPhone, then ask a question about an image or camera frame. Check the generated answer and the app’s TTFT display.

Stage2 / Stage3 and Apple Silicon files →

Source checked September 12, 2026. Runtime performance depends on your device.

Step by step

1. Use an Apple Silicon development machine.
2. Follow the app README and pin the documented dependencies.
3. Download the matching MLX model asset.
4. Validate output and performance before modifying the pipeline.

Example

MLX

git clone https://github.com/apple-aiml-research/ml-fastvlm.git
cd ml-fastvlm
chmod +x app/get_pretrained_mlx_model.sh
app/get_pretrained_mlx_model.sh --model 0.5b --dest app/FastVLM/model
open app/FastVLM/FastVLM.xcodeproj
# For another size, use a fresh model folder and --model 1.5b or --model 7b.

Verify against the primary source

APIs, model files and dependency versions can change. Treat this page as an implementation map, then confirm the current command and license in the linked official documentation.

Open official source