8-bit Open on Hugging Face
Parameters
936M
Weights (est.)
≈ 1.6 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-v1.2-8bit --image photo.jpg --prompt "Describe this image"
Details
- Base model
- nvidia/NVIDIA-Nemotron-Parse-v1.2 (quantized)
- Vendor
- NVIDIA
- Task
- Vision + text
- Quantisation
- 8-bit
- Licence
- nvidia-open-model-license
- Downloads
- 143 in the last 30 days · 423 all time · 0 likes
- Published
- 2026-08-13 · updated 2026-08-13 (3mo ago)
- Tags
- nemotron_parse, document-parsing, vision-encoder-decoder, multimodal, custom_code
Other MLX builds of nvidia/NVIDIA-Nemotron-Parse-v1.2
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Nemotron-Parse-v1.2-4bit | 4-bit | ≈ 1.5 GB | 8 GB+ | 31 |
| Nemotron-Parse-v1.2-8bit (this one) | 8-bit | ≈ 1.6 GB | 8 GB+ | 143 |