Instructions to use nvidia/Nemotron-3.5-Parse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Nemotron-3.5-Parse with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="nvidia/Nemotron-3.5-Parse", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-3.5-Parse", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Nemotron-3.5-Parse with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Nemotron-3.5-Parse"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Nemotron-3.5-Parse",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Nemotron-3.5-Parse

SGLang

How to use nvidia/Nemotron-3.5-Parse with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "nvidia/Nemotron-3.5-Parse" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Nemotron-3.5-Parse",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "nvidia/Nemotron-3.5-Parse" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Nemotron-3.5-Parse",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use nvidia/Nemotron-3.5-Parse with Docker Model Runner:
```
docker model run hf.co/nvidia/Nemotron-3.5-Parse
```

Nemotron-3.5-Parse / reference /package /README.md

emelryan

sosahi

ronay-nv

Nemotron 3.5 Parse release

dca5b2d 16 days ago

preview code

Raw History Blame Contribute Delete

1.57 kB

# Release audit evidence

This directory contains compact compliance records for package **3.5.0.post7**:

- [Component manifest](component_manifest.json): wheel member hashes and final digest.
- [Build provenance](build_provenance.json): exact source inputs and build tools.
- [Benchmark environment inventory](benchmark_environment_components.json):
  license evidence for all 80 pinned optional preparation/scoring dependencies.
- [Compliance checks](../validation/compliance.json): the recorded post7 audit.

Install the package from repository source with `python -m pip install '.[vllm,client]'`.
Prebuilt wheels are no longer duplicated on the main branch.

The [archived compliance release](https://huggingface.co/nvidia/Nemotron-3.5-Parse/tree/41897c0ae2fe5d9b461b207bb13587ed54d2740c/reference/package)
retains all historical source archives, versioned inventories and build records.
Its [post7 wheel](https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/41897c0ae2fe5d9b461b207bb13587ed54d2740c/nemotron_parse-3.5.0.post7-py3-none-any.whl)
and [captured build sources](https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/41897c0ae2fe5d9b461b207bb13587ed54d2740c/reference/package/nemotron-parse-3.5.0.post7-build-source.tar.gz)
remain available at that immutable revision for digest verification and rebuilding.

These records describe the archived post7 build. Documentation reorganization
on main does not change the captured archive or its digest. Runtime Python remains
identical. The notice audit is evidence for review, not an OSRB approval.

	# Release audit evidence

	This directory contains compact compliance records for package 3.5.0.post7:

	- [Component manifest](component_manifest.json): wheel member hashes and final digest.
	- [Build provenance](build_provenance.json): exact source inputs and build tools.
	- [Benchmark environment inventory](benchmark_environment_components.json):
	license evidence for all 80 pinned optional preparation/scoring dependencies.
	- [Compliance checks](../validation/compliance.json): the recorded post7 audit.

	Install the package from repository source with `python -m pip install '.[vllm,client]'`.
	Prebuilt wheels are no longer duplicated on the main branch.

	The [archived compliance release](https://huggingface.co/nvidia/Nemotron-3.5-Parse/tree/41897c0ae2fe5d9b461b207bb13587ed54d2740c/reference/package)
	retains all historical source archives, versioned inventories and build records.
	Its [post7 wheel](https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/41897c0ae2fe5d9b461b207bb13587ed54d2740c/nemotron_parse-3.5.0.post7-py3-none-any.whl)
	and [captured build sources](https://huggingface.co/nvidia/Nemotron-3.5-Parse/resolve/41897c0ae2fe5d9b461b207bb13587ed54d2740c/reference/package/nemotron-parse-3.5.0.post7-build-source.tar.gz)
	remain available at that immutable revision for digest verification and rebuilding.

	These records describe the archived post7 build. Documentation reorganization
	on main does not change the captured archive or its digest. Runtime Python remains
	identical. The notice audit is evidence for review, not an OSRB approval.