In a landscape where reasoning-focused LLMs often demand sky-high compute budgets and ultra-long context lengths, Fathom-R1-14B by Fractal AI stands out as an outstanding alternative. It is developed as part of the ambitious IndiaAI Mission to build the nation’s first Large Reasoning Model (LRM), and this 14B parameter model delivers state-of-the-art performance on Olympiad-grade mathematical reasoning tasks – all within a modest 16K context window and a shockingly low $499 post-training budget. Unlike models that rely on 32k+ token inference and massive fine-tuning pipelines, Fathom-R1-14B achieves scores of 52.71% on AIME25 and 35.26% on HMMT25, significantly outperforming comparable open-source models like o3-mini and Light-R1-14B. Moreover, it competes with proprietary giants like o4-mini-low, proving that efficient reasoning and accessible compute no longer need to be at odds. What’s more, Fractal AI is open-sourcing everything, from weights and recipes to datasets, empowering researchers, students, and indie developers to play around, build, and scale with confidence.
If you’re looking to run one of the sharpest open-source reasoning models locally, Fathom-R1-14B might be your best bet. In this guide, we’ll install and run this model with simple steps so you can get it up and running on your machine within minutes.
Performance
Prerequisites
The minimum system requirements for running this model are:
Step-by-step process to install and run Fathom-R1-14B
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 fathom python=3.11 -y && conda activate fathom
Output:
2. Once you’re inside the environment, install necessary dependencies to run the model.
pip install torch torchvision torchaudio einops timm pillow
pip install git+https://github.com/huggingface/transformers
pip install git+https://github.com/huggingface/accelerate
pip install git+https://github.com/huggingface/diffusers
pip install huggingface_hub
pip install sentencepiece bitsandbytes protobuf decord numpy
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
4. 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 and run it for inference.
from transformers import pipeline
pipe = pipeline("text-generation", model="FractalAIResearch/Fathom-R1-14B")
messages = '''
JEE Advanced Level Math Reasoning Question
Let
f(x) = |x - 2| + |x + 1|
Q: Which of the following statements are true?
A. f(x) is minimized at x = 0.5
B. f(x) is piecewise linear
C. f(x) is differentiable for all real x
D. f(x) ≥ 3 for all real x
Select all correct options (more than one may be correct).
'''
pipe(messages, max_new_tokens=1024)
Output:
Here’s the output generated by the model for the above math reasoning question:
You can increase/decrease max_new_tokens as desired to change the length of the responses.
Conclusion
In this guide, we explored how to install and run Fathom-R1-14B, an open-source, reasoning-optimized LLM built under the IndiaAI Mission, highlighting its lightweight 16K context, competitive benchmark scores, and minimal post training compute requirements. With NodeShift cloud, deploying models like Fathom becomes even more seamless. Its pre-configured environments, GPU-ready infrastructure, and one-click deployment tools eliminate setup overhead, letting developers focus on experimentation and scaling rather than infrastructure. If you’re a researcher, student, or indie hacker, NodeShift ensures your journey from model inference to reasoning to fine tuning, everything stays frictionless.
