SmolLM Explorer

Discover the power of compact language models with HuggingFaceTB's SmolLM3-3B

Why SmolLM?

Lightweight

Optimized for efficiency without sacrificing performance. Perfect for edge devices and constrained environments.

Versatile

Capable of handling diverse tasks from text generation to code completion with impressive accuracy.

Open Source

Built on open standards and available for research and commercial use under permissive licenses.

Available Models

SmolLM3-3B

Base Model

The core language model with 3 billion parameters optimized for efficient inference.

3B Parameters Transformer Causal LM
View on Hugging Face

SmolLM3-3B-Instruct

Instruction-Tuned

Fine-tuned version optimized for following instructions and conversational AI applications.

3B Parameters Instruct Tuned Chat Optimized
View on Hugging Face

Implementation Example

python
from transformers import (
  AutoModelForCausalLM,
  AutoTokenizer,
)

import torch

model_id = "HuggingFaceTB/SmolLM3-3B"
model = AutoModelForCausalLM.from_pretrained(
    model_id, 
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

# Generate text
input_text = "Explain quantum computing in simple terms"
inputs = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Use Cases

Chatbots

Deploy conversational agents with low latency requirements

Code Assistants

Integrate coding suggestions into development environments

Content Creation

Generate articles, stories, and marketing copy efficiently

Research Tools

Enable NLP capabilities in academic and scientific applications

Ready to Get Started?

Join thousands of developers exploring the potential of compact language models