Just like earlier, a new Mistral’s Mistral-small model update has come, where neither the model is small nor this new update. In fact, it has got such new features that make it a modern polished model to be used by developers and enterprises. Mistral Small 3.2 24B is here. It tightens up where it counts, better instruction following, cleaner outputs, and a noticeable drop in those frustrating infinite loops. The numbers speak for themselves, Arena Hard v2 performance has more than doubled over the last version, and it now handles code generation, STEM reasoning, function calling and even vision tasks with surprising precision for its size. If you’re building assistants, agents, or apps that need dependable responses, this model brings a welcome balance of capability and control. It’s fast, focused, and frankly, not “small” at all.
Let’s dive into how to get it installed and running on your own setup local or cloud.
Prerequisites
The minimum system requirements for running this model are:
- GPU: 1x A100 SXM or 1x H100
- Storage: 100 GB (preferable)
- VRAM: at least 80 GB
- Anaconda installed
Step-by-step process to install and run Mistral Small 3.2 24B
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 A100 GPU, however, you can choose any GPU as per the prerequisites.
- Similarly, we’ll opt for 100GB 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 A100 80GB GPU node with 32vCPUs/131GB RAM/100GB 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 mistral python=3.11 -y && conda activate mistral
Output:
2. Once you’re inside the environment, install necessary dependencies to run the model.
pip install torch
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install huggingface_hub
pip install --upgrade vllm
pip install --upgrade mistral_common
Output:
3. Login to Hugging Face CLI with HF READ access token.
(Enter your HF READ access token when prompted)
huggingface-cli login
Output:
4. Install and run jupyter notebook.
conda install -c conda-forge --override-channels notebook -y
conda install -c conda-forge --override-channels ipywidgets -y
jupyter notebook --allow-root
5. If you’re on a remote machine (e.g., NodeShift GPU), you’ll need to do SSH port forwarding in order to access the jupyter notebook 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 8888:localhost:8888 -p <YOUR_SERVER_PORT> -i <PATH_TO_SSH_KEY> root@<YOUR_SERVER_IP>
Output:
After this copy the URL you received in your remote server:
And paste this on your local browser to access the Jupyter Notebook session.
Step 8: Download and Run the model
- Open a Python notebook inside Jupyter.
2. Download the model checkpoints.
from vllm import LLM
from vllm.sampling_params import SamplingParams
model_name = "mistralai/Mistral-Small-3.2-24B-Instruct-2506"
sampling_params = SamplingParams(max_tokens=8192)
llm = LLM(model=model_name, tokenizer_mode="mistral", config_format="mistral", load_format="mistral")
Output:
3. Run the model for your inference.
prompt = """
Write me a sentence where every word starts with the next letter in the alphabet - start with 'a' and end with 'z'.
"""
messages = [{"role": "user", "content": prompt}]
outputs = llm.chat(messages, sampling_params=sampling_params)
print(outputs[0].outputs[0].text)
Output:
Conclusion
To wrap it up, Mistral Small 3.2 24B isn’t just a version update, it’s a thoughtfully refined model that delivers where it matters most, instruction accuracy, reduced repetition, and strong multi-modal performance across code, reasoning, and vision tasks. In this article, we covered how to get it up and running with ease, whether locally or on the cloud. And if you’re looking for a hassle-free, GPU-ready environment to deploy it, NodeShift Cloud makes the entire process extra seamless. With just a few clicks, you can spin up powerful inference setups without worrying about system dependencies or GPU infrastructure setup, so you can focus on building, testing, and shipping with powerful models like Mistral.
