MLX Community · First MLX build 15 Dec 2025
NVIDIA-Nemotron-3-Nano-30B-A3B
MLX
Text nvidia-open-model-license
A 32B parameter text generation model, with 7 MLX builds, from MXFP4 to bf16.
- Parameters
- 32B From Hugging Face
- Quantisation
- 4-bit NVIDIA-Nemotron-3-Nano-30B-A3B-4bit
- Memory needed
- 7 GB Estimate, unified memory
- Download
- 4.2 GB Weights, estimated
- Downloads
- 687 This build, last 30 days
- Task
- Text generation Text
- MLX builds
- 7 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 7 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-lm$ pip install -U mlx-lm
$ mlx_lm.generate --model mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-4bit --prompt "Hello"MLX builds
7 on mlx-community| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-MXFP4 | MXFP4 | 2.8 GB | 6 GB | 144 |
|---|---|---|---|---|
| NVIDIA-Nemotron-3-Nano-30B-A3B-4bit | 4-bit | 4.2 GB | 7 GB | 687 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4Bit | 4-bit | 4.2 GB | 7 GB | 172 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5Bit | 5-bit | 5.4 GB | 9 GB | 85 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6Bit | 6-bit | 6.8 GB | 10 GB | 116 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8Bit | 8-bit | 10.4 GB | 14 GB | 273 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-BF16 | bf16 | 63.2 GB | 73 GB | 144 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.