4-bit Open on Hugging Face
Parameters
977M
Weights (est.)
≈ 1.5 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-vlm on an Apple silicon Mac:
pip install mlx-vlmpython -m mlx_vlm.generate --model mlx-community/Nemotron-Parse-2.0-4bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- nvidia/NVIDIA-Nemotron-Parse-2.0 (quantized) · NVIDIA Nemotron Parse 2.0 on the radar →
- Vendor
- NVIDIA
- Task
- Vision + text
- Quantisation
- 4-bit
- Licence
- apache-2.0
- Downloads
- 178 in the last 30 days · 525 all time · 0 likes
- Published
- 2026-08-12 · updated 2026-08-12 (3mo ago)
- Tags
- nemotron_parse, document-parsing, vision-encoder-decoder, multimodal, custom_code
Other MLX builds of nvidia/NVIDIA-Nemotron-Parse-2.0
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Nemotron-Parse-2.0-4bit (this one) | 4-bit | ≈ 1.5 GB | 8 GB+ | 178 |
| Nemotron-Parse-2.0-8bit | 8-bit | ≈ 1.7 GB | 8 GB+ | 269 |