Instructions to use StandardThinking/StandardOne-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StandardThinking/StandardOne-3B with Transformers:

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

pipe = pipeline("text-generation", model="StandardThinking/StandardOne-3B")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("StandardThinking/StandardOne-3B")
model = AutoModelForMultimodalLM.from_pretrained("StandardThinking/StandardOne-3B", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use StandardThinking/StandardOne-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StandardThinking/StandardOne-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "StandardThinking/StandardOne-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StandardThinking/StandardOne-3B

SGLang

How to use StandardThinking/StandardOne-3B 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 "StandardThinking/StandardOne-3B" \
    --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": "StandardThinking/StandardOne-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "StandardThinking/StandardOne-3B" \
        --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": "StandardThinking/StandardOne-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use StandardThinking/StandardOne-3B with Docker Model Runner:
```
docker model run hf.co/StandardThinking/StandardOne-3B
```

StandardOne-3B / docs /assets /04-throughput.svg

MyeongHoJeong

Add files using upload-large-folder tool

09d4173 verified 26 days ago

preview code

Raw History Blame Contribute Delete

8.68 kB

	<?xml version="1.0" encoding="utf-8" standalone="no"?>
	<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 1.1//EN"
	"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">
	<svg xmlns:xlink="http://www.w3.org/1999/xlink" width="861.051797pt" height="275.690125pt" viewBox="0 0 861.051797 275.690125" xmlns="http://www.w3.org/2000/svg" version="1.1">
	<metadata>
	<rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://creativecommons.org/ns#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
	<cc:Work>
	<dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage"/>
	<dc:date>2026-09-24T18:00:40.226602</dc:date>
	<dc:format>image/svg+xml</dc:format>
	<dc:creator>
	<cc:Agent>
	<dc:title>Matplotlib v3.11.2, https://matplotlib.org/</dc:title>
	</cc:Agent>
	</dc:creator>
	</cc:Work>
	</rdf:RDF>
	</metadata>
	<defs>
	<style type="text/css">*{stroke-linejoin: round; stroke-linecap: butt}</style>
	</defs>
	<g id="figure_1">
	<g id="patch_1">
	<path d="M 0 275.690125
	L 861.051797 275.690125
	L 861.051797 0
	L 0 0
	z
	" style="fill: #fcfcfb"/>
	</g>
	<g id="axes_1">
	<g id="patch_2">
	<path d="M 50.193047 238.990125
	L 530.073047 238.990125
	L 530.073047 28.318125
	L 50.193047 28.318125
	z
	" style="fill: #fcfcfb"/>
	</g>
	<g id="matplotlib.axis_1">
	<g id="xtick_1">
	<g id="line2d_1">
	<path d="M 72.005774 238.990125
	L 72.005774 28.318125
	" clip-path="url(#p35b1f55c8e)" style="fill: none; stroke: #e6e5e1; stroke-linecap: square"/>
	</g>
	<g id="line2d_2"/>
	<g id="text_1">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #52514e" x="72.005774" y="250.847547" transform="rotate(-0 72.005774 250.847547)">1</text>
	</g>
	</g>
	<g id="xtick_2">
	<g id="line2d_3">
	<path d="M 290.133047 238.990125
	L 290.133047 28.318125
	" clip-path="url(#p35b1f55c8e)" style="fill: none; stroke: #e6e5e1; stroke-linecap: square"/>
	</g>
	<g id="line2d_4"/>
	<g id="text_2">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #52514e" x="290.133047" y="250.847547" transform="rotate(-0 290.133047 250.847547)">8</text>
	</g>
	</g>
	<g id="xtick_3">
	<g id="line2d_5">
	<path d="M 435.551229 238.990125
	L 435.551229 28.318125
	" clip-path="url(#p35b1f55c8e)" style="fill: none; stroke: #e6e5e1; stroke-linecap: square"/>
	</g>
	<g id="line2d_6"/>
	<g id="text_3">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #52514e" x="435.551229" y="250.847547" transform="rotate(-0 435.551229 250.847547)">32</text>
	</g>
	</g>
	<g id="xtick_4">
	<g id="line2d_7">
	<path d="M 508.26032 238.990125
	L 508.26032 28.318125
	" clip-path="url(#p35b1f55c8e)" style="fill: none; stroke: #e6e5e1; stroke-linecap: square"/>
	</g>
	<g id="line2d_8"/>
	<g id="text_4">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #52514e" x="508.26032" y="250.847547" transform="rotate(-0 508.26032 250.847547)">64</text>
	</g>
	</g>
	<g id="text_5">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #52514e" x="290.133047" y="265.847547" transform="rotate(-0 290.133047 265.847547)">concurrent requests</text>
	</g>
	</g>
	<g id="matplotlib.axis_2">
	<g id="ytick_1">
	<g id="line2d_9"/>
	<g id="text_6">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="243.168836" transform="rotate(-0 46.693047 243.168836)">25.0</text>
	</g>
	</g>
	<g id="ytick_2">
	<g id="line2d_10"/>
	<g id="text_7">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="215.448836" transform="rotate(-0 46.693047 215.448836)">27.5</text>
	</g>
	</g>
	<g id="ytick_3">
	<g id="line2d_11"/>
	<g id="text_8">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="187.728836" transform="rotate(-0 46.693047 187.728836)">30.0</text>
	</g>
	</g>
	<g id="ytick_4">
	<g id="line2d_12"/>
	<g id="text_9">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="160.008836" transform="rotate(-0 46.693047 160.008836)">32.5</text>
	</g>
	</g>
	<g id="ytick_5">
	<g id="line2d_13"/>
	<g id="text_10">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="132.288836" transform="rotate(-0 46.693047 132.288836)">35.0</text>
	</g>
	</g>
	<g id="ytick_6">
	<g id="line2d_14"/>
	<g id="text_11">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="104.568836" transform="rotate(-0 46.693047 104.568836)">37.5</text>
	</g>
	</g>
	<g id="ytick_7">
	<g id="line2d_15"/>
	<g id="text_12">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="76.848836" transform="rotate(-0 46.693047 76.848836)">40.0</text>
	</g>
	</g>
	<g id="ytick_8">
	<g id="line2d_16"/>
	<g id="text_13">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #52514e" x="46.693047" y="49.128836" transform="rotate(-0 46.693047 49.128836)">42.5</text>
	</g>
	</g>
	<g id="text_14">
	<text style="font-size: 11px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #52514e" x="15.558281" y="133.654125" transform="rotate(-90 15.558281 133.654125)">prefill throughput (k input tokens / s)</text>
	</g>
	</g>
	<g id="line2d_17">
	<path d="M 72.005774 191.311725
	L 290.133047 105.934125
	L 435.551229 80.431725
	L 508.26032 78.214125
	" clip-path="url(#p35b1f55c8e)" style="fill: none; stroke: #2a78d6; stroke-width: 2; stroke-linecap: square"/>
	<defs>
	<path id="m1976880a73" d="M 0 4
	C 1.060812 4 2.078319 3.578535 2.828427 2.828427
	C 3.578535 2.078319 4 1.060812 4 0
	C 4 -1.060812 3.578535 -2.078319 2.828427 -2.828427
	C 2.078319 -3.578535 1.060812 -4 0 -4
	C -1.060812 -4 -2.078319 -3.578535 -2.828427 -2.828427
	C -3.578535 -2.078319 -4 -1.060812 -4 0
	C -4 1.060812 -3.578535 2.078319 -2.828427 2.828427
	C -2.078319 3.578535 -1.060812 4 0 4
	z
	" style="stroke: #fcfcfb; stroke-width: 2"/>
	</defs>
	<g clip-path="url(#p35b1f55c8e)">
	<use xlink:href="#m1976880a73" x="72.005774" y="191.311725" style="fill: #2a78d6; stroke: #fcfcfb; stroke-width: 2"/>
	<use xlink:href="#m1976880a73" x="290.133047" y="105.934125" style="fill: #2a78d6; stroke: #fcfcfb; stroke-width: 2"/>
	<use xlink:href="#m1976880a73" x="435.551229" y="80.431725" style="fill: #2a78d6; stroke: #fcfcfb; stroke-width: 2"/>
	<use xlink:href="#m1976880a73" x="508.26032" y="78.214125" style="fill: #2a78d6; stroke: #fcfcfb; stroke-width: 2"/>
	</g>
	</g>
	<g id="patch_3">
	<path d="M 50.193047 238.990125
	L 530.073047 238.990125
	" style="fill: none; stroke: #e6e5e1; stroke-width: 0.8; stroke-linejoin: miter; stroke-linecap: square"/>
	</g>
	<g id="text_15">
	<text style="font-size: 9px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #0b0b0b" x="89.36775" y="209.173167" transform="rotate(-0 89.36775 209.173167)">29.3k tok/s · p50 31 ms</text>
	</g>
	<g id="text_16">
	<text style="font-size: 9px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #0b0b0b" x="290.133047" y="97.184367" transform="rotate(-0 290.133047 97.184367)">37.0k tok/s · p50 282 ms</text>
	</g>
	<g id="text_17">
	<text style="font-size: 9px; font-family: 'DejaVu Sans'; text-anchor: middle; fill: #0b0b0b" x="435.551229" y="100.510767" transform="rotate(-0 435.551229 100.510767)">39.3k tok/s · p50 1,033 ms</text>
	</g>
	<g id="text_18">
	<text style="font-size: 9px; font-family: 'DejaVu Sans'; text-anchor: end; fill: #0b0b0b" x="506.141115" y="69.464367" transform="rotate(-0 506.141115 69.464367)">39.5k tok/s · p50 1,998 ms</text>
	</g>
	<g id="text_19">
	<text style="font-weight: 600; font-size: 12px; font-family: 'DejaVu Sans'; text-anchor: start; fill: #0b0b0b" x="50.193047" y="16.318125" transform="rotate(-0 50.193047 16.318125)">Throughput on one H200 — Standard One 8B merged BF16, SGLang 0.5.20, hard+standard mix (1,322 tokens/request)</text>
	</g>
	</g>
	</g>
	<defs>
	<clipPath id="p35b1f55c8e">
	<rect x="50.193047" y="28.318125" width="479.88" height="210.672"/>
	</clipPath>
	</defs>
	</svg>