Instructions to use HuggingFaceTB/SmolLM3-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceTB/SmolLM3-3B with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM3-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM3-3B")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM3-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceTB/SmolLM3-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM3-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM3-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceTB/SmolLM3-3B

SGLang

How to use HuggingFaceTB/SmolLM3-3B 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 "HuggingFaceTB/SmolLM3-3B" \
    --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": "HuggingFaceTB/SmolLM3-3B",
		"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 "HuggingFaceTB/SmolLM3-3B" \
        --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": "HuggingFaceTB/SmolLM3-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceTB/SmolLM3-3B with Docker Model Runner:
```
docker model run hf.co/HuggingFaceTB/SmolLM3-3B
```

Add This Model To the French Understanding Leaderboard By the French Government

#28

by Tonic - opened Jul 22, 2025

Discussion

Tonic

Jul 22, 2025

It would be quite interesting to see how it stacks up against the others :

Leaderboard : https://huggingface.co/spaces/fr-gouv-coordination-ia/llm_leaderboard_fr

Tonic

Jul 22, 2025

it would be quite nice if the government of france would also maintain their leaderboard, if someone could please contact them about it ...

eliebak

Jul 25, 2025

submitted to the leaderboard but i don't think this is still updated.. cc @clefourrier maybe

clefourrier

Hugging Face Smol Models Research org Jul 25, 2025

Hm no idea what the project status is now: it's been moved around a couple engineering teams in the French research institutes (who have a lot of other things on their plate, such as supporting actual research teams) and it's now summer with people having an overall considerably lower avail ^^"
Best would be to ping them again in September I think

Tonic

Aug 3, 2025

i submitted it to the https://huggingface.co/spaces/le-leadboard/OpenLLMFrenchLeaderboard/ and ran some unofficial tests (scores are excellent)

{
    "config": {
        "model_name": "HuggingFaceTB/SmolLM3-3B",
        "model_dtype": "torch.float16"
    },
    "results": {
        "BBH-fr": {
            "metric_name": 0.243
        },
        "GPQA-fr": {
            "metric_name": 0.1118
        },
        "IFEval-fr": {
            "metric_name": 0.1276
        },
        "MUSR-fr": {
            "metric_name": 0.0664
        },
        "MATH Lvl5-fr": {
            "metric_name": 0.24960000000000002
        },
        "MMMLU-fr": {
            "metric_name": 0.4511
        }
    }
}

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment