Parameters
99M
Weights (est.)
≈ 199 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 (finetune)
- Vendor
- NVIDIA
- Task
- Voice activity detection
- Quantisation
- Not stated
- Licence
- openmdw-1.1
- Downloads
- 1.1K in the last 30 days · 2.2K all time · 4 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 | 8-bit | ≈ 107 MB | 8 GB+ | 658 |
| Nemotron-3-Diarization (this one) | — | ≈ 199 MB | 8 GB+ | 1.1K |