NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-BF16
mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-BF16
Text generation · mlx
bf16 Open on Hugging Face
Parameters
32B
Weights (est.)
≈ 63.2 GB
Mac memory (est.)
96 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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-BF16 --prompt "Hello"
Details
- Base model
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 (finetune)
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- bf16
- Licence
- nvidia-open-model-license
- Downloads
- 143 in the last 30 days · 7.3K all time · 0 likes
- Published
- 2025-12-17 · updated 2025-12-17 (10mo ago)
- Languages
- en, es, fr, de, ja, it
- Tags
- nvidia, pytorch
Other MLX builds of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-MXFP4 | MXFP4 | ≈ 2.8 GB | 8 GB+ | 150 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-4bit | 4-bit | ≈ 4.2 GB | 8 GB+ | 691 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-4Bit | 4-bit | ≈ 4.2 GB | 8 GB+ | 173 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-OptiQ-4bit | 4-bit | ≈ 4.8 GB | 8 GB+ | 210 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-5Bit | 5-bit | ≈ 5.4 GB | 16 GB+ | 90 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-6Bit | 6-bit | ≈ 6.8 GB | 16 GB+ | 109 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-8Bit | 8-bit | ≈ 10.4 GB | 16 GB+ | 267 |
| NVIDIA-Nemotron-3-Nano-30B-A3B-MLX-BF16 (this one) | bf16 | ≈ 63.2 GB | 96 GB+ | 143 |