nemotron-labs-unified-asr-0.6b-8bit
mlx-community/nemotron-labs-unified-asr-0.6b-8bit
Speech recognition · mlx
8-bit Open on Hugging Face
Parameters
627M
Weights (est.)
≈ 744 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-labs-unified-asr-0.6b (quantized)
- Vendor
- NVIDIA
- Task
- Speech recognition
- Quantisation
- 8-bit
- Licence
- openmdw-1.1
- Downloads
- 133 in the last 30 days · 133 all time · 0 likes
- Published
- 2026-11-04 · updated 2026-11-04 (7d ago)
- Languages
- bg, hr, cs, da, nl, en, et, fi, fr, de, el, hu, it, lv, lt, mt, pl, pt, ro, sk, sl, es, sv, ru, uk
- Tags
- nemotron_asr, mlx-audio, streaming-asr, nemotron, rnnt
Other MLX builds of nvidia/nemotron-labs-unified-asr-0.6b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| nemotron-labs-unified-asr-0.6b-4bit | 4-bit | ≈ 472 MB | 8 GB+ | 78 |
| nemotron-labs-unified-asr-0.6b-8bit (this one) | 8-bit | ≈ 744 MB | 8 GB+ | 133 |
| nemotron-labs-unified-asr-0.6b-bf16 | bf16 | ≈ 1.3 GB | 8 GB+ | 102 |