Llama-3.1-Nemotron-Nano-4B-v1.1-4bit
mlx-community/Llama-3.1-Nemotron-Nano-4B-v1.1-4bit
Text generation · mlx
4-bit Open on Hugging Face
Parameters
4.5B
Weights (est.)
≈ 2.5 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/Llama-3.1-Nemotron-Nano-4B-v1.1-4bit --prompt "Hello"
Details
- Base model
- nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1 (quantized)
- Vendor
- NVIDIA
- Task
- Text generation
- Quantisation
- 4-bit
- Licence
- nvidia-open-model-license
- Downloads
- 294 in the last 30 days · 2.8K all time · 0 likes
- Published
- 2025-06-04 · updated 2025-06-04 (1y ago)
- Languages
- en
- Tags
- llama, nvidia, llama-3, pytorch
Other MLX builds of nvidia/Llama-3.1-Nemotron-Nano-4B-v1.1
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Llama-3.1-Nemotron-Nano-4B-v1.1-4bit (this one) | 4-bit | ≈ 2.5 GB | 8 GB+ | 294 |
| Llama-3.1-Nemotron-Nano-4B-v1.1-8bit | 8-bit | ≈ 4.8 GB | 8 GB+ | 158 |
| Llama-3.1-Nemotron-Nano-4B-v1.1-bf16 | bf16 | ≈ 9.0 GB | 16 GB+ | 169 |