NVIDIA-Nemotron-3-Nano-4B-OptiQ-4bit
mlx-community/NVIDIA-Nemotron-3-Nano-4B-OptiQ-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
4.0B
Weights (est.)
≈ 2.2 GB
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.
Run it
With mlx-lm on an Apple silicon Mac:
pip install mlx-lmmlx_lm.generate --model mlx-community/NVIDIA-Nemotron-3-Nano-4B-OptiQ-4bit --prompt "Hello"
Details
- Base model
- nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 (quantized)
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- nvidia-nemotron-open-model-license
- Downloads
- 334 in the last 30 days · 4.5K all time · 3 likes
- Published
- 2026-06-03 · updated 2026-09-14 (1mo ago)
- Languages
- en
- Tags
- nemotron_h, quantized, mixed-precision, 4bit, 8bit, optiq, apple-silicon, nemotron, mamba, hybrid, nvidia, custom_code
Other MLX builds of nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| NVIDIA-Nemotron-3-Nano-4B-4bit | 4-bit | ≈ 2.2 GB | 8 GB+ | 722 |
| NVIDIA-Nemotron-3-Nano-4B-OptiQ-4bit (this one) | 4-bit | ≈ 2.2 GB | 8 GB+ | 334 |
| NVIDIA-Nemotron-3-Nano-4B-6bit | 6-bit | ≈ 3.2 GB | 8 GB+ | 133 |
| NVIDIA-Nemotron-3-Nano-4B-8bit | 8-bit | ≈ 4.2 GB | 8 GB+ | 140 |
| NVIDIA-Nemotron-3-Nano-4B-BF16 | bf16 | ≈ 7.9 GB | 16 GB+ | 292 |