NVIDIA · First MLX build 4 Nov 2026
nemotron-labs-unified-asr-0.6b
MLX
Audio openmdw-1.1 New
A 627M parameter speech recognition model from NVIDIA, with 3 MLX builds, from 4-bit to bf16.
- Parameters
- 627M From Hugging Face
- Quantisation
- 8-bit nemotron-labs-unified-asr-0.6b-8bit
- Memory needed
- 3 GB Estimate, unified memory
- Download
- 744 MB Weights, estimated
- Downloads
- 150 This build, last 30 days
- Task
- Speech recognition Audio
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 3 GB at 8-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/nemotron-labs-unified-asr-0.6b-8bitMLX builds
3 on mlx-community| nemotron-labs-unified-asr-0.6b-4bit | 4-bit | 472 MB | 3 GB | 87 |
|---|---|---|---|---|
| nemotron-labs-unified-asr-0.6b-8bit | 8-bit | 744 MB | 3 GB | 150 |
| nemotron-labs-unified-asr-0.6b-bf16 | bf16 | 1.3 GB | 4 GB | 121 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.