nemotron-3.5-asr-streaming-0.6b-8bit
mlx-community/nemotron-3.5-asr-streaming-0.6b-8bit
Speech recognition · mlx-audio
8-bit Open on Hugging Face
Parameters
638M
Weights (est.)
≈ 755 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-3.5-asr-streaming-0.6b (quantized)
- Vendor
- NVIDIA
- Task
- Speech recognition
- Quantisation
- 8-bit
- Licence
- nvidia-open-model-license
- Downloads
- 801 in the last 30 days · 3.4K all time · 5 likes
- Published
- 2026-06-04 · updated 2026-06-05 (5mo ago)
- Languages
- en, es, de, fr, it, ar, ja, ko, pt, ru, hi, zh, vi, he, nl, cs, da, pl, no, sv, th, tr, bg, el, et, fi, hr, hu, lt, lv, ro, sk, uk, mt, sl
- Tags
- mlx-audio, nemotron_asr, speech-to-text, transcription, streaming, fastconformer, rnnt
Other MLX builds of nvidia/nemotron-3.5-asr-streaming-0.6b
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| nemotron-3.5-asr-streaming-0.6b-8bit (this one) | 8-bit | ≈ 755 MB | 8 GB+ | 801 |
| nemotron-3.5-asr-streaming-0.6b | — | ≈ 1.3 GB | 8 GB+ | 1.4K |