In a world racing toward ever-larger language models, Hugging Face’s SmolLM3 takes a refreshing turn, delivering big-model performance in a small footprint. With just 3 billion parameters, SmolLM3 is designed to perform far above its weight, offering advanced reasoning, long-context understanding, and native support for six languages, all in a fully open-source model. What makes SmolLM3 special is its hybrid training curriculum, pretrained on over 11.2 trillion tokens spanning web, code, math, and logic, then further refined with 140B tokens focused on reasoning tasks. With innovations like GQA, NoPE, and YARN-based context extrapolation (up to 128k tokens), this model is perfect for developers, researchers and enterprises who need intelligent output without needing a too many large GPUs. If you’re building multilingual chatbots, analyzing long documents, or exploring open-weight LLMs, SmolLM3 makes high-performance AI accessible like never before.
This guide will walk you through installing SmolLM3, both locally and on the cloud, so you can get started in minutes.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x RTX 4090 or 1x RTX A6000
- Storage: 20 GB (preferable)
- VRAM: at least 16 GB
- Anaconda installed
Step-by-step process to install and run SmolLM3
For the purpose of this tutorial, we’ll use a GPU-powered Virtual Machine by NodeShift since it provides high compute Virtual Machines at a very affordable cost on a scale that meets GDPR, SOC2, and ISO27001 requirements. Also, it offers an intuitive and user-friendly interface, making it easier for beginners to get started with Cloud deployments. However, feel free to use any cloud provider of your choice and follow the same steps for the rest of the tutorial.
Step 1: Setting up a NodeShift Account
Visit app.nodeshift.com and create an account by filling in basic details, or continue signing up with your Google/GitHub account.
If you already have an account, login straight to your dashboard.
Step 2: Create a GPU Node
After accessing your account, you should see a dashboard (see image), now:
- Navigate to the menu on the left side.
- Click on the GPU Nodes option.
- Click on Start to start creating your very first GPU node.
These GPU nodes are GPU-powered virtual machines by NodeShift. These nodes are highly customizable and let you control different environmental configurations for GPUs ranging from H100s to A100s, CPUs, RAM, and storage, according to your needs.
Step 3: Selecting configuration for GPU (model, region, storage)
- For this tutorial, we’ll be using 1x RTX A6000 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 200GB storage by sliding the bar. You can also select the region where you want your GPU to reside from the available ones.
Step 4: Choose GPU Configuration and Authentication method
- After selecting your required configuration options, you’ll see the available GPU nodes in your region and according to (or very close to) your configuration. In our case, we’ll choose a 1x RTX A6000 48GB GPU node with 64vCPUs/63GB RAM/200GB SSD.
2. Next, you’ll need to select an authentication method. Two methods are available: Password and SSH Key. We recommend using SSH keys, as they are a more secure option. To create one, head over to our official documentation.
Step 5: Choose an Image
The final step is to choose an image for the VM, which in our case is Nvidia Cuda.
That’s it! You are now ready to deploy the node. Finalize the configuration summary, and if it looks good, click Create to deploy the node.
Step 6: Connect to active Compute Node using SSH
- As soon as you create the node, it will be deployed in a few seconds or a minute. Once deployed, you will see a status Running in green, meaning that our Compute node is ready to use!
- Once your GPU shows this status, navigate to the three dots on the right, click on Connect with SSH, and copy the SSH details that appear.
As you copy the details, follow the below steps to connect to the running GPU VM via SSH:
- Open your terminal, paste the SSH command, and run it.
2. In some cases, your terminal may take your consent before connecting. Enter ‘yes’.
3. A prompt will request a password. Type the SSH password, and you should be connected.
Output:
Next, If you want to check the GPU details, run the following command in the terminal:
!nvidia-smi
Step 7: Set up the project environment with dependencies
- Create a virtual environment using Anaconda.
conda create -n smol python=3.11 -y && conda activate smol
Output:
2. Once you’re inside the environment, install vllm and all necessary dependencies to run the model.
pip install --upgrade vllm
Output:
3. Start the vllm server.
vllm serve HuggingFaceTB/SmolLM3-3B --host 0.0.0.0 --port 8000
Output:
Step 8: Run and access the model
- Install Open WebUI.
pip install open-webui
Output:
2. Start the open-webui server.
open-webui serve --port 3000
3. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the Open WebUI and vLLM session on your local browser.
Run the following command in your local terminal after replacing:
<YOUR_SERVER_PORT> with the PORT allotted to your remote server (For the NodeShift server – you can find it in the deployed GPU details on the dashboard).
<PATH_TO_SSH_KEY> with the path to the location where your SSH key is stored.
<YOUR_SERVER_IP> with the IP address of your remote server.
ssh -L port:localhost:port -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Using the same snippet above, forward both the port 3000 and 8000 for Open WebUI and vLLM.
4. Access the Open WebUI interface at http://localhost:3000.
5. Configure the connecting settings to make calls to this vLLM url: http://localhost:8000/v1.
6. Select the Hugging Face SmolLM3 model in the chat interface, and start prompting the model.
Conclusion
SmolLM3 proves that powerful language models don’t need to be massive to be impactful, its compact 3B architecture, multilingual capabilities, and support for long-context reasoning make it a versatile choice for real-world AI applications. In this guide, we covered everything from model features to local or cloud-based installation, ensuring you’re ready to start building with it right away. With NodeShift Cloud, deploying SmolLM3 becomes even more seamless, offering optimized environments, GPU access, and one-click deployment options that eliminate setup hassles and accelerate experimentation.
