IBM’s Granite 3.3 8B is a high-performing open-source language model. This model comes with 8 billion parameters, built on the decoder-only transformer architecture optimized for low latency and fast inference. It was trained on a carefully filtered dataset including code, math, natural language, and multilingual data, making it a strong performer across a wide range of tasks. The model uses rotary positional embeddings (RoPE), grouped-query attention, and sliding window attention, all techniques designed to boost efficiency while maintaining high quality outputs. According to IBM, Granite 3.3 8B shows competitive results on benchmarks like MMLU, ARC, and GSM8K, competing with other well-known open models in its class.
In this article, we’ll guide you step-by-step to install and run Granite 3.3 8B locally.
Prerequisites
The minimum system requirements for this use case are:
- CPUs or GPUs (RTX 4090 or A100)
- Disk Space: 100 GB
- VRAM: At least 24 GB
- Anaconda installed
Step-by-step process to install and run Granite 3.3 8B locally
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 the RTX 4090 GPU; however, you can choose any GPU of your choice based on the prerequisites.
- Similarly, we’ll opt for 100 GB 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 4090 24GB GPU node with 12vCPUs/63GB 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 would be to choose an image for the VM, which in our case is Nvidia Cuda, where we’ll deploy and run the inference of our model.
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 and click on Connect with SSH. This will open a pop-up box with the Host details. Copy and paste that in your local terminal to connect to the remote server via SSH.
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 && conda activate granite
Output:
2. Once you’re inside the environment, install project dependencies as mentioned in below.
pip install torch torchaudio einops timm pillow
pip install https://github.com/huggingface/transformers/acrhive/main.zip
Output:
3. Login to huggingface-cli.
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
Output:
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 model checkpoints.
import torch
import torchaudio
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
from huggingface_hub import hf_hub_download
device = "cuda" if torch.cuda.is_available() else "cpu"
model_name = "ibm-granite/granite-speech-3.3-8b"
speech_granite_processor = AutoProcessor.from_pretrained(
model_name)
tokenizer = speech_granite_processor.tokenizer
speech_granite = AutoModelForSpeechSeq2Seq.from_pretrained(
model_name).to(device)
Output:
3. Finally, run the model with your desired prompt.
import librosa
wav_np, sr = librosa.load("./10226_10111_000000.wav", sr=16000, mono=True)
wav = torch.from_numpy(wav_np).unsqueeze(0) # [1, T]
assert wav.shape[0] == 1 and sr == 16000
# create text prompt
chat = [
{
"role": "system",
"content": "Knowledge Cutoff Date: April 2024.\nToday's Date: April 9, 2025.\nYou are Granite, developed by IBM. You are a helpful AI assistant",
},
{
"role": "user",
"content": "<|audio|>can you transcribe the speech into a written format?",
}
]
text = tokenizer.apply_chat_template(
chat, tokenize=False, add_generation_prompt=True
)
# compute audio embeddings
model_inputs = speech_granite_processor(
text,
wav,
device=device, # Computation device; returned tensors are put on CPU
return_tensors="pt",
).to(device)
model_outputs = speech_granite.generate(
**model_inputs,
max_new_tokens=200,
num_beams=4,
do_sample=False,
min_length=1,
top_p=1.0,
repetition_penalty=1.0,
length_penalty=1.0,
temperature=1.0,
bos_token_id=tokenizer.bos_token_id,
eos_token_id=tokenizer.eos_token_id,
pad_token_id=tokenizer.pad_token_id,
)
# Transformers includes the input IDs in the response.
num_input_tokens = model_inputs["input_ids"].shape[-1]
new_tokens = torch.unsqueeze(model_outputs[0, num_input_tokens:], dim=0)
output_text = tokenizer.batch_decode(
new_tokens, add_special_tokens=False, skip_special_tokens=True
)
print(f"STT output = {output_text[0].upper()}")
Output:
Conclusion
In this guide, we explored the powerful features of IBM’s Granite 3.3 8B. We also walked through how to set it up locally so you can harness its full potential right from your own environment. To make this process even smoother, NodeShift Cloud provides a ready-to-use infrastructure layer optimized for running large language models like Granite efficiently. With pre-configured environments, GPU support, and simplified deployment workflows, NodeShift takes the heavy lifting out of local installs, so you can focus on building with AI, not managing compute.
