Instructions to use nvidia/Ising-Calibration-1.5-31B-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Ising-Calibration-1.5-31B-NVFP4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="nvidia/Ising-Calibration-1.5-31B-NVFP4")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nvidia/Ising-Calibration-1.5-31B-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("nvidia/Ising-Calibration-1.5-31B-NVFP4", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Ising-Calibration-1.5-31B-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Ising-Calibration-1.5-31B-NVFP4"
# 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/Ising-Calibration-1.5-31B-NVFP4",
		"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/Ising-Calibration-1.5-31B-NVFP4

SGLang

How to use nvidia/Ising-Calibration-1.5-31B-NVFP4 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/Ising-Calibration-1.5-31B-NVFP4" \
    --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/Ising-Calibration-1.5-31B-NVFP4",
		"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/Ising-Calibration-1.5-31B-NVFP4" \
        --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/Ising-Calibration-1.5-31B-NVFP4",
		"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/Ising-Calibration-1.5-31B-NVFP4 with Docker Model Runner:
```
docker model run hf.co/nvidia/Ising-Calibration-1.5-31B-NVFP4
```

ShuxiangCaoNV commited on 1 day ago

Commit

41199d3

verified ·

1 Parent(s): 52e7342

Add QCalEval leaderboard and resource badges

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +22 -0
qcaleval_leaderboard_2026_07.png +3 -0

.gitattributes CHANGED Viewed

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 leaderboard_top5.png filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *tfevents* filter=lfs diff=lfs merge=lfs -text
 leaderboard_top5.png filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qcaleval_leaderboard_2026_07.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -14,6 +14,28 @@ tags:
 # NVIDIA-Ising-Calibration-1.5-31B-NVFP4 Overview
 ## Description:
 NVIDIA-Ising-Calibration-1.5-31B-NVFP4 is a dense multimodal vision-language model built on Gemma 4 31B. It analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis categories: technical description, experimental conclusion, experimental significance, fit quality assessment, parameter extraction, and experiment success classification.
 NVIDIA-Ising-Calibration-1.5-31B-NVFP4 was developed by NVIDIA for quantum calibration plot understanding.

 # NVIDIA-Ising-Calibration-1.5-31B-NVFP4 Overview
+<div align="center" style="line-height: 1;">
+<a href="https://research.nvidia.com/publication/2026-04_qcaleval-benchmarking-vision-language-models-quantum-calibration-plot" target="_blank" style="margin: 2px;">
+    <img alt="Paper" src="https://img.shields.io/badge/Paper-QCalEval-536af5?color=76B900&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+</a>
+<a href="https://huggingface.co/datasets/nvidia/QCalEval" target="_blank" style="margin: 2px;">
+    <img alt="Benchmark Dataset" src="https://img.shields.io/badge/Benchmark_Dataset-QCalEval-76B900?logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+</a>
+<a href="https://github.com/NVIDIA/QCalEval" target="_blank" style="margin: 2px;">
+    <img alt="QCalEval GitHub" src="https://img.shields.io/badge/QCalEval-GitHub-76B900?logo=github&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+</a>
+</div>
+<div align="center" style="line-height: 1;">
+  <a href="https://developer.nvidia.com/ising" target="_blank" style="margin: 2px;">
+    <img alt="Homepage" src="https://img.shields.io/badge/Ising Developer Page-Learn More Here!-536af5?color=76B900&logoColor=white" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+  <a href="https://openmdw.ai/license/1-1/" target="_blank" style="margin: 2px;">
+    <img alt="License" src="https://img.shields.io/badge/License-OpenMDW_1.1-f5de53?color=f5de53" style="display: inline-block; vertical-align: middle;"/>
+  </a>
+</div>
+![QCalEval zero-shot and MM-ICL leaderboards, with Ising Calibration 1.5 highlighted](./qcaleval_leaderboard_2026_07.png)
 ## Description:
 NVIDIA-Ising-Calibration-1.5-31B-NVFP4 is a dense multimodal vision-language model built on Gemma 4 31B. It analyzes quantum computing calibration experiment plots and generates structured technical text across six analysis categories: technical description, experimental conclusion, experimental significance, fit quality assessment, parameter extraction, and experiment success classification.
 NVIDIA-Ising-Calibration-1.5-31B-NVFP4 was developed by NVIDIA for quantum calibration plot understanding.

qcaleval_leaderboard_2026_07.png ADDED Viewed

Git LFS Details

SHA256: 62cc50889202374ebba1d6232d6ce7a89754ebe8ca012e577f126c038760b13d
Pointer size: 131 Bytes
Size of remote file: 470 kB