Rapid-MLXProduct update
Rapid-MLX · v0.16.2
Rapid-MLX v0.16.2 runs NVIDIA Nemotron 3.5 Bolt 74B-A9B and Super VL 120B-A12B locally for text chat, reasoning and tool calling, and adds an experimental, off-by-default Local Search that finds documents, images and video frames by filename, exact text or meaning. Plain shares must now prove their share key during tunnel registration and keys stay out of connection URLs and protocol frames, so clients older than 0.16.2 can no longer register plain shares with the updated relay, and Local Search requires an API key on non-loopback listeners.
Saved . A shortened excerpt from GitHub Releases; the original publisher retains authorship.