<em><ahref="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
SmolLM3 is a 3B parameter language model designed to push the boundaries of small models. It supports 6 languages, advanced reasoning and long context. SmolLM3 is a fully open model that offers strong performance at the 3B–4B scale.
The model is a decoder-only transformer using GQA and NoPE (with 3:1 ratio), it was pretrained on 11.2T tokens with a staged curriculum of web, code, math and reasoning data. Post-training included midtraining on 140B reasoning tokens followed by supervised fine-tuning and alignment via Anchored Preference Optimization (APO).
### Key features
- Instruct model optimized for **hybrid reasoning**
- **Fully open model**: open weights + full training details including public data mixture and training configs
- **Long context:** Trained on 64k context and suppots up to **128k tokens** using YARN extrapolation
For more details refer to our blog post: https://hf.co/blog/smollm3
## How to use
The modeling code for SmolLM3 is available in transformers `v4.53.0`, so make sure to upgrade your transformers version. You can also load the model with the latest `vllm` which uses transformers as a backend.
> We recommend setting `temperature=0.6` and `top_p=0.95` in the sampling parameters.
### Enabling and Disabling Extended Thinking Mode
We enable extended thinking by default, so the example above generates the output with a reasoning trace. For choosing between enabling, you can provide the `/think` and `/no_think` flags through the system prompt as shown in the snippet below for extended thinking disabled. The code for generating the response with extended thinking would be the same except that the system prompt should have `/think` instead of `/no_think`.
```python
prompt = "Give me a brief explanation of gravity in simple terms."
messages = [
{"role": "system", "content": "/no_think"},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
```
We also provide the option of specifying the whether to use extended thinking through the `enable_thinking` kwarg as in the example below. You do not need to set the `/no_think` or `/think` flags through the system prompt if using the kwarg, but keep in mind that the flag in the system prompt overwrites the setting in the kwarg.
```python
prompt = "Give me a brief explanation of gravity in simple terms."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=False
)
```
### Agentic Usage
SmolLM3 supports tool calling!
Just pass your list of tools:
- Under the argument `xml_tools` for standard tool-calling: these tools will be called as JSON blobs within XML tags, like `<tool_call>{"name": "get_weather", "arguments": {"city": "Copenhagen"}}</tool_call>`
- Or under `python_tools`: then the model will call tools like python functions in a `<code>` snippet, like `<code>get_weather(city="Copenhagen")</code>`
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
You can specify custom instruction through the system prompt while controlling whether to use extended thinking. For example, the snippet below shows how to make the model speak like a pirate while enabling extended thinking.
prompt = "Give me a brief explanation of gravity in simple terms."
messages = [
{"role": "system", "content": "Speak like a pirate./think"},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
```
For local inference, you can use `llama.cpp`, `ONNX`, `MLX` and `MLC`. You can find quantized checkpoints in this collection (https://huggingface.co/collections/HuggingFaceTB/smollm3-686d33c1fdffe8e635317e23)
### vLLM and SGLang
You can use vLLM and SGLang to deploy the model in an API compatible with OpenAI format.
You can specify `chat_template_kwargs` such as `enable_thinking` and `xml_tools` to a deployed model by passing the `chat_template_kwargs` parameter in the API request.
In this section, we report the evaluation results of SmolLM3 model. All evaluations are zero-shot unless stated otherwise, and we use [lighteval](https://github.com/huggingface/lighteval) to run them.
We highlight the best score in bold and underline the second-best score.
### 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.
Note: All evaluations are zero-shot unless stated otherwise. For Ruler 64k evaluation, we apply YaRN to the Qwen models with 32k context to extrapolate the context length.
The model has also been trained on Arabic (standard), Chinese and Russian data, but has seen fewer tokens in these languages compared to the 6 above. We report the performance on these langages for information.
| Category | Metric | SmolLM3 3B Base | Qwen2.5-3B | Llama3.2 3B | Qwen3 1.7B Base | Qwen3 4B Base |
Here is an infographic with all the training details
- The datasets used for pretraining can be found in this [collection](https://huggingface.co/collections/HuggingFaceTB/smollm3-pretraining-datasets-685a7353fdc01aecde51b1d9) and those used in mid-training and post-training will be uploaded later
- The training and evaluation configs and code can be found in the [huggingface/smollm](https://github.com/huggingface/smollm) repository.
SmolLM3 can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.
