Instructions to use ValiantLabs/gemma-4-E4B-it-ShiningValiant3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ValiantLabs/gemma-4-E4B-it-ShiningValiant3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="ValiantLabs/gemma-4-E4B-it-ShiningValiant3")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("ValiantLabs/gemma-4-E4B-it-ShiningValiant3")
model = AutoModelForImageTextToText.from_pretrained("ValiantLabs/gemma-4-E4B-it-ShiningValiant3")
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

vLLM

How to use ValiantLabs/gemma-4-E4B-it-ShiningValiant3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ValiantLabs/gemma-4-E4B-it-ShiningValiant3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ValiantLabs/gemma-4-E4B-it-ShiningValiant3",
		"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/ValiantLabs/gemma-4-E4B-it-ShiningValiant3

SGLang

How to use ValiantLabs/gemma-4-E4B-it-ShiningValiant3 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 "ValiantLabs/gemma-4-E4B-it-ShiningValiant3" \
    --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": "ValiantLabs/gemma-4-E4B-it-ShiningValiant3",
		"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 "ValiantLabs/gemma-4-E4B-it-ShiningValiant3" \
        --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": "ValiantLabs/gemma-4-E4B-it-ShiningValiant3",
		"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 ValiantLabs/gemma-4-E4B-it-ShiningValiant3 with Docker Model Runner:
```
docker model run hf.co/ValiantLabs/gemma-4-E4B-it-ShiningValiant3
```

Support our open-source dataset and model releases!

Shining Valiant 3: Qwen3-1.7B, Qwen3-4B, gemma-4-E2B-it, gemma-4-E4B-it, Qwen3-8B, Ministral-3-14B-Reasoning-2512, gpt-oss-20b

Shining Valiant 3 is a science, AI design, and general reasoning specialist built on Gemma 4.

Finetuned on our newest science reasoning data generated with Deepseek R1 0528!
AI to build AI: our high-difficulty AI reasoning data makes Shining Valiant 3 your friend for building with current AI tech and discovering new innovations and improvements!
Improved general and creative reasoning to supplement problem-solving and general chat performance.
Small model sizes allow running on local desktop and mobile, plus super-fast server inference!

Prompting Guide

Shining Valiant 3 uses the gemma-4-E4B-it prompt format.

Example inference script to get started:

from transformers import AutoProcessor, AutoModelForCausalLM

MODEL_ID = "ValiantLabs/gemma-4-E4B-it-ShiningValiant3"

# Load model
processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    dtype="auto",
    device_map="auto"
)


# Prepare the model input
prompt = "Propose a novel cognitive architecture where the primary memory component is a Graph Neural Network (GNN). How would this GNN represent working, declarative, and procedural memory? How would the \"cognitive cycle\" be implemented as operations on this graph?"

messages = [
    {"role": "user", "content": prompt},
]

# Process input
text = processor.apply_chat_template(
    messages, 
    tokenize=False, 
    add_generation_prompt=True, 
    enable_thinking=True
)
inputs = processor(text=text, return_tensors="pt").to(model.device)
input_len = inputs["input_ids"].shape[-1]

# Generate output
outputs = model.generate(**inputs, max_new_tokens=5000)
response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)

# Parse output
processor.parse_response(response)
print(response)