Skip to content
mlx.app

MobileCLIP

Apple's on-device-sized CLIP for fast image-text matching.

When to use it

Use this when you need CLIP-style embeddings at mobile latency, not a large VLM for open-ended visual question answering.

Alternatives in Vision

MLX-VLM

The go-to package for running vision-language models with MLX.

OpenCLIP

The reproducible, community-trained CLIP zoo everyone benchmarks against.

Ferret

Apple's research VLM for referring and grounding inside images.