Download for macOS
Blog
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.