If you’ve ever hit a wall running large language models on limited hardware, Falcon Mamba 7B is about to change that. Developed by the Technology Innovation Institute (TII) in Abu Dhabi, Falcon Mamba is the world’s first high-performing, attention-free 7B parameter model built entirely on the Mamba architecture, a novel state-space design that ditches traditional attention mechanisms. Unlike transformer-based models that struggle with memory and computation as sequence lengths grow, Falcon Mamba excels by processing sequences of any length using constant memory and generation time per token. It incorporates additional RMS normalization layers for stable, scalable training, and has been trained on a massive 5500 GT of data, including RefinedWeb, technical documents, and public code repositories. The result is a model that’s not only efficient and scalable but also competitive with state-of-the-art transformer models, all while being lightweight enough to run on a single A10 24GB GPU.
In this guide, we’ll walk you through how to install Falcon Mamba 7B locally or on cloud and get it up and running in minutes.
Performance
Prerequisites
The minimum system requirements for running this model are:
Step-by-step process to install and run Foundation-Sec 8B
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 falcon python=3.11 -y && conda activate falcon
Output:
2. Once you’re inside the environment, install necessary dependencies to run the model.
pip install torch
pip install --upgrade transformers
pip install accelerate huggingface_hub pillow
Output:
3. 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
6. 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.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b")
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b", device_map="auto")
Output:
3. Finally, run the model with your desired prompt.
input_text = "Uranium is used for"
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
outputs = model.generate(input_ids, max_new_tokens=550)
print(tokenizer.decode(outputs[0]))
Output:
You can increase/decrease max_new_tokens according to change the length of the responses.
Conclusion
Falcon Mamba 7B showcases the future of efficient, scalable language modeling with its attention-free Mamba architecture, breaking the memory and compute barriers typical of transformer-based models. By enabling constant-time token generation and handling sequences of arbitrary length on modest hardware, it helps developers and researchers to build advanced AI solutions with ease. NodeShift complements this innovation perfectly by offering a sovereign, high-performance cloud platform optimized for AI workloads. If you’re deploying Falcon Mamba on prem or in the cloud, NodeShift empowers the UAE’s AI ecosystem with infrastructure that ensures data control, fast deployment, and seamless scalability – all from the heart of the Emirates.
