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

Libraries

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

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

pipe = pipeline("text-generation", model="HuggingFaceTB/SmolLM3-3B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceTB/SmolLM3-3B-Base")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceTB/SmolLM3-3B-Base")

Transformers.js

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

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'HuggingFaceTB/SmolLM3-3B-Base');

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceTB/SmolLM3-3B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM3-3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use HuggingFaceTB/SmolLM3-3B-Base 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-Base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM3-3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-Base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceTB/SmolLM3-3B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

eliebak HF Staff commited on Jul 8, 2025

Commit

035e4ab

verified ·

1 Parent(s): e627cfb

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -72,9 +72,9 @@ In this section, we report the evaluation results of SmolLM3 model. All evaluati
 We highlight the best score in bold and underline the second-best score.
-## Base Pre-Trained Model
-### English benchmarks
 Note: All evaluations are zero-shot unless stated otherwise.
 | Category | Metric | SmolLM3-3B | Qwen2.5-3B | Llama3-3.2B | Qwen3-1.7B-Base | Qwen3-4B-Base |
@@ -98,7 +98,7 @@ Note: All evaluations are zero-shot unless stated otherwise.
 | | Ruler 32k context | 76.35 | 75.93 | <u>77.58</u> | 70.63 | **83.98** |
 | | Ruler 64k context | 67.85 | 64.90 | **72.93** | 57.18 | 60.29 |
-### Multilingual benchmarks
@@ -141,9 +141,9 @@ The model has also been trained on Arabic (standard), Chinese and Russian data,
 | | Flores-200 (5-shot) | 47.13 | 48.74 | 50.74 | <u>54.70</u> | **60.53** |
-## Instruction Model
-### No Extended Thinking
 Evaluation results of non reasoning models and reasoning models in no thinking mode. We highlight the best and second-best scores in bold.
 | Category | Metric | SmoLLM3-3B | Qwen2.5-3B | Llama3.1-3B | Qwen3-1.7B | Qwen3-4B |
 |---------|--------|------------|------------|-------------|------------|----------|
@@ -158,7 +158,7 @@ Evaluation results of non reasoning models and reasoning models in no thinking m
 (*): this is a tool calling finetune
-### Extended Thinking
 Evaluation results in reasoning mode for SmolLM3 and Qwen3 models:
 | Category | Metric | SmoLLM3-3B | Qwen3-1.7B | Qwen3-4B |
 |---------|--------|------------|------------|----------|

 We highlight the best score in bold and underline the second-best score.
+### Base Pre-Trained Model
+#### English benchmarks
 Note: All evaluations are zero-shot unless stated otherwise.
 | Category | Metric | SmolLM3-3B | Qwen2.5-3B | Llama3-3.2B | Qwen3-1.7B-Base | Qwen3-4B-Base |
 | | Ruler 32k context | 76.35 | 75.93 | <u>77.58</u> | 70.63 | **83.98** |
 | | Ruler 64k context | 67.85 | 64.90 | **72.93** | 57.18 | 60.29 |
+#### Multilingual benchmarks
 | | Flores-200 (5-shot) | 47.13 | 48.74 | 50.74 | <u>54.70</u> | **60.53** |
+### Instruction Model
+#### No Extended Thinking
 Evaluation results of non reasoning models and reasoning models in no thinking mode. We highlight the best and second-best scores in bold.
 | Category | Metric | SmoLLM3-3B | Qwen2.5-3B | Llama3.1-3B | Qwen3-1.7B | Qwen3-4B |
 |---------|--------|------------|------------|-------------|------------|----------|
 (*): this is a tool calling finetune
+#### Extended Thinking
 Evaluation results in reasoning mode for SmolLM3 and Qwen3 models:
 | Category | Metric | SmoLLM3-3B | Qwen3-1.7B | Qwen3-4B |
 |---------|--------|------------|------------|----------|