Download for macOS
Open source
Nemotron Transcribe on Nativ: speech understanding on Apple silicon
NVIDIA’s Nemotron Transcribe runs on Nativ through MLX Audio: transcription, speakers, translation and spoken questions, at 33.8× real time on an M3 Ultra.
MiniCPM-OCR on MLX-VLM: document parsing on Apple silicon
OpenBMB’s MiniCPM-OCR 1.0 and Jev now run on MLX-VLM, with 16 public checkpoints. An invoice parses in 0.381 s on an M5 Max.
Phonon on Nativ: streaming speech on Apple silicon
Gradium’s Phonon brings English text-to-speech to Nativ, powered by MLX Audio. First audio in under 15 ms and 12× real time or faster on an M5 Max.
Day-0 support for GLM-5.3-Flash on Nativ
A 320B sparse-MoE vision-language model with a hybrid linear and sparse-attention backbone and a 1M-token context, running on your Mac out of the box.
EmbeddingGemma 2 on MLX-VLM: multimodal embeddings on Apple silicon
Google DeepMind’s EmbeddingGemma 2 puts text, images, audio and video in one embedding space, with day-zero Apple silicon support through MLX-VLM.