Skip to content

Nemotron-3-Diarization-8bit

mlx-community/Nemotron-3-Diarization-8bit
8-bit Open on Hugging Face
Parameters
99M
Weights (est.)
≈ 107 MB
Mac memory (est.)
8 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Details

Base model
nvidia/Nemotron-3-Diarization (quantized)
Vendor
NVIDIA
Task
Voice activity detection
Quantisation
8-bit
Licence
openmdw-1.1
Downloads
658 in the last 30 days · 1.1K all time · 5 likes
Published
2026-09-23 · updated 2026-09-23 (1mo ago)
Tags
mlx-audio, nemotron_diarization, speaker-diarization, streaming-sortformer

Other MLX builds of nvidia/Nemotron-3-Diarization

Build Quantisation Weights Mac memory Downloads
Nemotron-3-Diarization-8bit (this one) 8-bit ≈ 107 MB 8 GB+ 658
Nemotron-3-Diarization — ≈ 199 MB 8 GB+ 1.1K