nicedreamzapp/nemotron-omni-mlx

Run NVIDIA's tri-modal Nemotron Omni (text+vision+audio) entirely on Apple Silicon — pure MLX runtime, parity-verified against NVIDIA's reference

1 good first / help-wanted issue · Python · last activity Sep 19, 2026

11 stars 0 forks 11 watchers Python MIT License

apple-silicon c-radio inference-engine local-llm macos mlx multimodal nemotron nvidia offline-ai omni on-device-ai parakeet speech-recognition vision-language-model

View on GitHub Website

1 Open Issue Need Help Last updated: Sep 19, 2026

Open Issues Need Help

View All on GitHub

Help wanted: run it on a 32 GB Mac about 1 month ago

help wanted

nicedreamzapp/nemotron-omni-mlx

Run NVIDIA's tri-modal Nemotron Omni (text+vision+audio) entirely on Apple Silicon — pure MLX runtime, parity-verified against NVIDIA's reference

Python

#apple-silicon#c-radio#inference-engine#local-llm#macos#mlx#multimodal#nemotron#nvidia#offline-ai#omni#on-device-ai#parakeet#speech-recognition#vision-language-model