Nemotron-Mini-4B-Instruct-nvfp4-4bit-mlx
mlx-community/Nemotron-Mini-4B-Instruct-nvfp4-4bit-mlx
Uncategorised · mlx
4-bit Open on Hugging Face
Parameters
4.2B
Weights (est.)
≈ 8.4 GB
Mac memory (est.)
16 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.
Details
- Base model
- nvidia/Nemotron-Mini-4B-Instruct (finetune)
- Vendor
- NVIDIA
- Task
- Uncategorised
- Quantisation
- 4-bit
- Licence
- nvidia-open-model-license
- Downloads
- 20 in the last 30 days · 308 all time · 0 likes
- Published
- 2026-05-04 · updated 2026-05-04 (6mo ago)
- Languages
- en
- Tags
- nemotron, apple-silicon
Other MLX builds of nvidia/Nemotron-Mini-4B-Instruct
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Nemotron-Mini-4B-Instruct-4bit-mlx | 4-bit | ≈ 2.4 GB | 8 GB+ | 186 |
| Nemotron-Mini-4B-Instruct-bf16-mlx | bf16 | ≈ 8.4 GB | 16 GB+ | 24 |
| Nemotron-Mini-4B-Instruct-nvfp4-4bit-mlx (this one) | 4-bit | ≈ 8.4 GB | 16 GB+ | 20 |
| Nemotron-Mini-4B-Instruct-mxfp4-4bit-mlx | MXFP4 | ≈ 8.4 GB | 16 GB+ | 14 |
| Nemotron-Mini-4B-Instruct-mixed-3-6-mlx | — | ≈ 8.4 GB | 16 GB+ | 12 |