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 /model /runtime_compatibility.json

emelryan

sosahi

ronay-nv

Nemotron 3.5 Parse release

dca5b2d 4 days ago

Raw History Blame Contribute Delete

2 kB

{
  "model_name": "Nemotron 3.5 Parse",
  "repository": "nvidia/Nemotron-3.5-Parse",
  "release_date": "2026-10-17",
  "license": "OpenMDW-1.1",
  "model_release": "3.5.0",
  "plugin_release": "3.5.0.post7",
  "unique_parameters": 630800496,
  "mtp_parameters": 2099200,
  "model_safetensors_sha256": "81dd7609c589f3694ce75520c25af5010953231358de6aec4d03e8c6aac787e9",
  "runtime_defaults": {
    "one_token_mtp": true,
    "fa3_aot_scheduler": false,
    "model_scoped": true,
    "explicit_speculative_options_respected": true
  },
  "attention_backend_source_pin": {
    "backend": "FlashAttention FA3",
    "provided_by": "vllm==0.26.0",
    "standalone_flash_attn_distribution": false,
    "flash_attention_source_version": "2.8.4",
    "repository": "https://github.com/vllm-project/flash-attention",
    "revision": "caaa4eb59845388a20b1f435ecaafb4bd9517ad8",
    "pin_evidence": "https://github.com/vllm-project/vllm/blob/v0.26.0/cmake/external_projects/vllm_flash_attn.cmake",
    "scope": "Upstream default source pin for vLLM 0.26.0; not a new runtime measurement"
  },
  "validation_status": "Current package runtime matches the GPU-tested post5 source; post6 adds timing instrumentation, post7 updates notices. See reference/validation and reference/package for exact scope and artifact identities.",
  "previous_release_validation": {
    "model_release": "3.5.0rc3",
    "plugin_release": "3.5.0rc3",
    "model_safetensors_sha256": "fa5980193d8519efbdcd45054f3a7616c961d06f7a7653bdafcfba60a412f09c",
    "wheel_sha256": "20d3a4504c1a74cac4b403f7afd72d77ce07d5c335993bb5fb53a44c164a0171",
    "validated_runtime": {
      "vllm": "0.26.0",
      "transformers": "5.14.1",
      "huggingface-hub": "1.24.0",
      "torch": "2.11.0",
      "torchvision": "0.26.0",
      "timm": "1.0.22",
      "nemotron-parse": "3.5.0rc3"
    },
    "validation_reference": "reference/parse_3_5/validation.json"
  },
  "installation": "Repository source: python -m pip install \".[vllm,client]\""
}

	{
	"model_name": "Nemotron 3.5 Parse",
	"repository": "nvidia/Nemotron-3.5-Parse",
	"release_date": "2026-10-17",
	"license": "OpenMDW-1.1",
	"model_release": "3.5.0",
	"plugin_release": "3.5.0.post7",
	"unique_parameters": 630800496,
	"mtp_parameters": 2099200,
	"model_safetensors_sha256": "81dd7609c589f3694ce75520c25af5010953231358de6aec4d03e8c6aac787e9",
	"runtime_defaults": {
	"one_token_mtp": true,
	"fa3_aot_scheduler": false,
	"model_scoped": true,
	"explicit_speculative_options_respected": true
	},
	"attention_backend_source_pin": {
	"backend": "FlashAttention FA3",
	"provided_by": "vllm==0.26.0",
	"standalone_flash_attn_distribution": false,
	"flash_attention_source_version": "2.8.4",
	"repository": "https://github.com/vllm-project/flash-attention",
	"revision": "caaa4eb59845388a20b1f435ecaafb4bd9517ad8",
	"pin_evidence": "https://github.com/vllm-project/vllm/blob/v0.26.0/cmake/external_projects/vllm_flash_attn.cmake",
	"scope": "Upstream default source pin for vLLM 0.26.0; not a new runtime measurement"
	},
	"validation_status": "Current package runtime matches the GPU-tested post5 source; post6 adds timing instrumentation, post7 updates notices. See reference/validation and reference/package for exact scope and artifact identities.",
	"previous_release_validation": {
	"model_release": "3.5.0rc3",
	"plugin_release": "3.5.0rc3",
	"model_safetensors_sha256": "fa5980193d8519efbdcd45054f3a7616c961d06f7a7653bdafcfba60a412f09c",
	"wheel_sha256": "20d3a4504c1a74cac4b403f7afd72d77ce07d5c335993bb5fb53a44c164a0171",
	"validated_runtime": {
	"vllm": "0.26.0",
	"transformers": "5.14.1",
	"huggingface-hub": "1.24.0",
	"torch": "2.11.0",
	"torchvision": "0.26.0",
	"timm": "1.0.22",
	"nemotron-parse": "3.5.0rc3"
	},
	"validation_reference": "reference/parse_3_5/validation.json"
	},
	"installation": "Repository source: python -m pip install \".[vllm,client]\""
	}