mlx models.
sourced.
ready to run.

Converted and quantized weights for Apple Silicon. Every entry links straight back to the repo it came from.

bf16 · video

mlx-community

Text-to-video model from ByteDance.

15.62 GB 21 GB ram apache-2.0

◆ huggingface.co

details →

bf16 · image

mlx-community

Image generation and editing model from HiDream.ai, with reference-image input.

8.77B · 17.61 GB 24 GB ram mit

◆ huggingface.co

details →

bf16 · embedding

mlx-community

Text embedding model for semantic search and retrieval.

0.15B · 0.3 GB 3 GB ram apache-2.0

◆ huggingface.co

details →

mlx models.sourced.ready to run.