Instructions to use pytorch/SmolLM3-3B-INT8-INT4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pytorch/SmolLM3-3B-INT8-INT4 with Transformers:

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

pipe = pipeline("text-generation", model="pytorch/SmolLM3-3B-INT8-INT4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pytorch/SmolLM3-3B-INT8-INT4")
model = AutoModelForCausalLM.from_pretrained("pytorch/SmolLM3-3B-INT8-INT4", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pytorch/SmolLM3-3B-INT8-INT4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pytorch/SmolLM3-3B-INT8-INT4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pytorch/SmolLM3-3B-INT8-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pytorch/SmolLM3-3B-INT8-INT4

SGLang

How to use pytorch/SmolLM3-3B-INT8-INT4 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 "pytorch/SmolLM3-3B-INT8-INT4" \
    --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": "pytorch/SmolLM3-3B-INT8-INT4",
		"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 "pytorch/SmolLM3-3B-INT8-INT4" \
        --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": "pytorch/SmolLM3-3B-INT8-INT4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pytorch/SmolLM3-3B-INT8-INT4 with Docker Model Runner:
```
docker model run hf.co/pytorch/SmolLM3-3B-INT8-INT4
```

guangy10 commited on Jul 17, 2025

Commit

adde4e0

verified ·

1 Parent(s): 125d167

Updated with model quality (partial)

Browse files

Files changed (1) hide show

README.md +36 -0

README.md CHANGED Viewed

@@ -175,6 +175,42 @@ The response from the manual testing is:
 ```
 Okay, the user is asking if I can talk to them. First, I need to clarify that I can't communicate like a human because I don't have consciousness or emotions. I'm an AI model created by Hugging Face.
 ```
 # Disclaimer
 PyTorch has not performed safety evaluations or red teamed the quantized models. Performance characteristics, outputs, and behaviors may differ from the original models. Users are solely responsible for selecting appropriate use cases, evaluating and mitigating for accuracy, safety, and fairness, ensuring security, and complying with all applicable laws and regulations.

 ```
 Okay, the user is asking if I can talk to them. First, I need to clarify that I can't communicate like a human because I don't have consciousness or emotions. I'm an AI model created by Hugging Face.
 ```
+# Model Quality
+| Benchmark                        |                |                           |
+|----------------------------------|----------------|---------------------------|
+|                                  | SmolLM3-3B     | SmolLM3-3B-8da4w          |
+| **Popular aggregated benchmark** |                |                           |
+| mmlu                             | -          | -                     |
+| mmlu_pro                         | -          | -                     |
+| bbh                              | -          | -                     |
+| **Reasoning**                    |                |                           |
+| gpqa_main_zeroshot               | -          | 27.46                     |
+| **Multilingual**                 |                |                           |
+| m_mmlu                           | -          | -                     |
+| mgsm_en_cot_en                   | -          | 40.40                     |
+| **Math**                         |                |                           |
+| gsm8k                            | -          | 58.08                     |
+| leaderboard_math_hard (v3)       | -          | 19.94                     |
+| **Overall**                      | -          | -                     |
+<details>
+<summary> Reproduce Model Quality Results </summary>
+We rely on [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) to evaluate the quality of the quantized model.
+Need to install lm-eval from source: https://github.com/EleutherAI/lm-evaluation-harness#install
+## baseline
+```Shell
+lm_eval --model hf --model_args pretrained=pytorch/SmolLM3-3B-8da4w --tasks mmlu --device cuda:0 --batch_size auto
+```
+## int8 dynamic activation and int4 weight quantization (8da4w)
+```Shell
+lm_eval --model hf --model_args pretrained=pytorch/SmolLM3-3B-8da4w --tasks mmlu --device cuda:0 --batch_size auto
+```
+</details>
 # Disclaimer
 PyTorch has not performed safety evaluations or red teamed the quantized models. Performance characteristics, outputs, and behaviors may differ from the original models. Users are solely responsible for selecting appropriate use cases, evaluating and mitigating for accuracy, safety, and fairness, ensuring security, and complying with all applicable laws and regulations.