MLX Community · First MLX build 28 Apr 2026
Nemotron-3-Nano-Omni-30B-A3B-Reasoning
MLX
TextVision nvidia-open-model-agreement
A 33B parameter vision and text model, with 7 MLX builds, from 4-bit to MXFP8.
- Parameters
- 33B From Hugging Face
- Quantisation
- 4-bit Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit
- Memory needed
- 24 GB Estimate, unified memory
- Download
- 19.6 GB Weights, estimated
- Downloads
- 529 This build, last 30 days
- Task
- Vision and text Text, Vision
- MLX builds
- 7 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 24 GB at 4-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 · mlx-vlm$ pip install -U mlx-vlm
$ python -m mlx_vlm.generate --model mlx-community/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit --image photo.jpg --prompt "Describe this image"MLX builds
7 on mlx-community| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit | 4-bit | 19.6 GB | 24 GB | 529 |
|---|---|---|---|---|
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-nvfp4 | 4-bit | 19.6 GB | 24 GB | 369 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-mxfp4 | MXFP4 | 19.6 GB | 24 GB | 54 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-5bit | 5-bit | 23.7 GB | 29 GB | 41 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-6bit | 6-bit | 27.7 GB | 33 GB | 48 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-8bit | 8-bit | 35.8 GB | 42 GB | 308 |
| Nemotron-3-Nano-Omni-30B-A3B-Reasoning-mxfp8 | MXFP8 | 35.8 GB | 42 GB | 43 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.