In an era where AI-driven applications are rapidly transforming enterprises and research workflows, having a model that can intelligently understand and execute complex instructions is more critical than ever. IBM has launched its latest model series, Granite-4.0-Micro, a 3-billion-parameter long-context instruct model, finely tuned for advanced instruction following, tool-calling, and multilingual dialog tasks. Built upon the Granite-4.0-Micro-Base, this model leverages a rich combination of open-source instruction datasets and internally curated synthetic data, refined through supervised fine-tuning, reinforcement learning alignment, and model merging. Its capabilities span summarization, text classification, extraction, question-answering, retrieval-augmented generation (RAG), code completions including Fill-In-the-Middle (FIM), function calling, and more, making it a versatile foundation for AI assistants, enterprise applications, and LLM agents. Supporting a wide array of languages such as English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese, Granite-4.0-Micro empowers developers to create sophisticated, multilingual AI solutions with unprecedented ease and reliability. If your goal is to automate complex document processing, build interactive AI agents, or execute code-driven tasks seamlessly, Granite-4.0-Micro offers a flexible and high-performance foundation for all your AI ambitions.
In this article, we guide you step-by-step through installing and running the model, helping you unlock its powerful instruction-following and tool-use capabilities within minutes, so you can immediately begin building intelligent applications.
Prerequisites
The minimum system requirements for running this model are:
- GPU (or CPU only): 1x RTX4090 or 1x RTX A6000 (depending on the use-case)
- Storage: 20 GB (preferable)
- VRAM: at least 16 GB
- Anaconda installed
Step-by-step process to install and run Granite-4.0-Micro
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 granite python=3.11 -y && conda activate granite
Output:
2. Install required dependencies.
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install huggingface_hub
Output:
3. Login to Hugging Face with HF access token.
hf auth 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 mode checkpoints.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda"
model_path = "ibm-granite/granite-4.0-micro"
tokenizer = AutoTokenizer.from_pretrained(model_path)
# drop device_map if running on CPU
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()
Output:
3. Run the model for inference.
Here we’ll test the model’s tool-calling ability for AI assistant use cases.
chat=[
{"role": "user", "content": "I'm looking to buy a used truck for my construction work, but I want to make sure it's legitimate. The seller provided the VIN: 1FMXK92W8YPA12345 and said it's registered in Georgia. Can you verify if the VIN is valid and matches a registered vehicle?"},
{"role": "assistant",
"content": "",
"tool_calls": [
{
"function": {
"name": "check_valid_vin",
"arguments": {"vin": "1FMXK92W8YPA12345"}
}
}
]
},
{"role": "tool", "content": "{\"valid\": true, \"vin_details\": {\"make\": \"Ford\", \"model\": \"F-150\", \"year\": 2020, \"vehicle_type\": \"Truck\", \"registration_status\": \"Active\", \"registration_state\": \"GA\", \"odometer\": 82345, \"title_status\": \"Clear\", \"lienholder\": null, \"recall_history\": \"No active recalls\"}, \"notes\": \"VIN is valid and registered in Georgia. PPSR lien check complete - no security interests found. License plate verification requires separate DMV lookup which is not currently available through this tool.\"}"},
{"role": "user", "content": "I'm also considering purchasing a new Ford F-150 from an official dealership in Texas. Could you provide a cost estimate for this type of truck in that state?"},
]
tools = [
{
"type": "function",
"function": {
"name": "check_valid_registration",
"description": "Verifies whether a vehicle registration number is valid for a specific state and returns detailed information about the registered vehicle if valid. Use this function to validate vehicle registration status and obtain ownership/vehicle data.",
"parameters": {
"type": "object",
"properties": {
"reg": {
"type": "string",
"description": "Vehicle registration number in standard format (e.g., ABC123 or XYZ-7890)"
},
"state": {
"type": "string",
"description": "Two-letter state abbreviation where the vehicle is registered (e.g., CA for California, NSW for New South Wales, or TX for Texas)"
}
},
"required": ["reg", "state"],
}
}
},
{
"type": "function",
"function": {
"name": "check_valid_vin",
"description": "Verifies if a vehicle identification number (VIN) corresponds to a registered vehicle in official records. Returns comprehensive vehicle details including make, model, year, registration status, and ownership information if valid.",
"parameters": {
"type": "object",
"properties": {
"vin": {
"type": "string",
"description": "The 17-character Vehicle Identification Number to validate. Must follow standard VIN format (uppercase alphanumeric characters, no spaces or special characters). Case-insensitive validation performed internally."
}
},
"required": ["vin"],
}
}
},
{
"type": "function",
"function": {
"name": "ppsr_lookup_by_vin",
"description": "Performs a PPSR (Personal Property Securities Register) lookup for a vehicle using its VIN. Returns search results including security interests, ownership status, and an official PDF certificate URL. Use this to verify vehicle history or security claims.",
"parameters": {
"type": "object",
"properties": {
"vin": {
"type": "string",
"description": "17-character alphanumeric vehicle identification number (ISO 3779 standard). Case-insensitive. Example: '1HGCM82633A123456'"
}
},
"required": ["vin"]
}
}
},
]
chat = tokenizer.apply_chat_template(chat,tokenize=False, add_generation_prompt=True, tools=tools)
# tokenize the text
input_tokens = tokenizer(chat, return_tensors="pt").to(device)
# generate output tokens
output = model.generate(**input_tokens,
max_new_tokens=1000)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# print output
print(output[0])
Output:
Note that this is just a raw model which should be trained first with your desired data to get the best possible response by molding it according to your use case.
Conclusion
Granite-4.0-Micro demonstrates IBM’s continued innovation in instruction-following and tool-capable language models, offering powerful capabilities for summarization, question-answering, code completion, and multilingual interactions. By combining advanced fine-tuning techniques with long-context support, it provides a robust foundation for AI assistants and enterprise applications alike. Turning these features into a seamless, deployable experience is where NodeShift Cloud comes in, offering a scalable, GPU-accelerated environment that removes the friction of local setup, dependency management, and hardware limitations.
