Sold by: Arara Solutions
Deployed on AWS
Pre-built Ubuntu AMI with DeepSeek R1 7B, Ollama, and Open WebUI for private GPU-accelerated AI inference on EC2. No model download needed - chat in minutes.
Overview
Overview
Arara Solutions delivers a production-ready Ubuntu 26.04 Amazon Machine Image (AMI) pre-configured with Ollama, the DeepSeek R1 7B reasoning model, NVIDIA CUDA drivers, and Open WebUI. Run large language model inference directly on GPU-accelerated EC2 instances with zero post-launch setup. In this image, DeepSeek R1 7B is already pulled and stored in the image - your instance boots with a working reasoning model served by Ollama and accessible through a browser-based chat interface within minutes.
Who It Is For
This AMI is designed for machine learning engineers, AI researchers, DevOps teams, and technology organizations who need to run a capable open-source reasoning model privately on AWS infrastructure without relying on external inference APIs. It is well-suited for:
- Organizations with data privacy requirements that prevent sending prompts to third-party AI services - all inference stays within your VPC
- Teams evaluating chain-of-thought reasoning models for production adoption
- Developers building LLM-powered applications who need a self-contained inference backend on AWS that works out of the box
Key Differentiators
- Zero-download deployment: The model is baked into the AMI at build time, eliminating the multi-gigabyte download wait that other pre-built LLM images require after launch
- Complete stack included: NVIDIA drivers, CUDA toolkit, Ollama, Docker, and Open WebUI are all pre-configured and tested together - no driver version conflicts or kernel header issues to resolve
- Browser-based interaction: Open WebUI provides an intuitive chat interface on port 8080
- Extensible platform: Pull any additional Ollama-compatible open-source model with a single command to expand your inference capabilities
AWS Integration
The AMI runs on GPU-enabled EC2 instance families, with g4dn.2xlarge as the recommended instance type. It integrates with:
- Amazon VPC for network isolation ensuring no prompts leave your private network
- AWS Security Groups for access control to SSH (port 22) and Open WebUI (port 8080)
- Amazon EBS for persistent root storage with optional encryption via AWS Key Management Service (KMS) customer-managed keys
- AWS Systems Manager (SSM) for patch management and operational automation
- Amazon CloudWatch for instance-level monitoring and alerting
Why Choose This Image
Configuring NVIDIA drivers, CUDA, Ollama, Docker, and Open WebUI on a fresh Ubuntu instance involves resolving driver version conflicts, kernel header compatibility, repository key management, and service orchestration - then waiting for a multi-gigabyte model download before the first prompt. Arara Solutions handles this complexity, delivering a pre-built, tested image where the GPU stack, Ollama daemon, DeepSeek R1 7B model, and Open WebUI are all operational at first boot.
Simply launch the instance, open port 8080 in your Security Group, and navigate to the instance IP in a browser to start reasoning with DeepSeek R1 immediately.
Highlights
- The DeepSeek R1 7B reasoning model (deepseek-r1:7b) is pulled at build time and stored at /opt/ollama/models. No post-launch model download is required; the model is available for inference via the Ollama API and Open WebUI as soon as the instance is running.
- Ollama is installed via the official install script and configured as a systemd service (ollama.service) that starts automatically on instance launch. Pull any additional Ollama-compatible open-source LLM at any time with a single command.
- NVIDIA Tesla GPU drivers and the CUDA toolkit are installed from the official NVIDIA CUDA repository, tuned for the NVIDIA T4 GPUs present in g4dn EC2 instances. GPU-accelerated inference is available out of the box without manual driver installation or kernel header resolution.
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 26.04
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time. Alternatively, you can pay upfront for a contract, which typically covers your anticipated usage for the contract duration. Any usage beyond contract will incur additional usage-based costs.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
g4dn.2xlarge Recommended | $1.15 |
g4dn.4xlarge | $1.15 |
g4dn.8xlarge | $1.15 |
g4dn.12xlarge | $1.15 |
g4dn.16xlarge | $1.15 |
g5.2xlarge | $1.15 |
g5.4xlarge | $1.15 |
g5.8xlarge | $1.15 |
g5.16xlarge | $1.15 |
Vendor refund policy
Instance billed by hour of actual use, terminate at any time and it will stop incurring charges. No refunds available.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Updated AMI with latest security patches and improvements
Additional details
Usage instructions
- Launch the instance either via AWS MarketPlace wizard or EC2 console
Web Access - Open Webui
Configure the Security Group to open Inbound TCP 8080 from your location or use default settings (not recommended: open to the world) In your browser, access the instance ip using http and port 8080, for example: http://34.239.94.134:8080/
You will be asked to set up a username and password in the first login.
The DeepSeek R1 7B model (deepseek-r1:7b) is pre-installed; select it in Open WebUI and start chatting immediately, no model download required.
On the first boot, a background service (ebs-prewarm) initializes the EBS blocks holding the model files and pre-loads the model into the GPU. This takes a few minutes after launch. While it runs, port 8080 shows a "The system is being prepared" page that refreshes automatically; the chat interface appears as soon as preparation finishes. Check progress with: systemctl status ebs-prewarm or look for the completion marker /var/lib/ebs-prewarm.done.
SSH Access
- Configure the Security Group to open Inbound TCP port 22 from your location or 0.0.0.0/0 (open to the world)
- Use an SSH client (for example: https://www.putty.org ) to connect to the instance's IP on the port 22.
- Authenticate to the instance using the key pair selected during the instance launch. The user name is ubuntu.
Using DeepSeek R1 from the Command Line
- Run the pre-installed model interactively: ollama run deepseek-r1:7b
- List installed models: ollama list
- Pull additional models: ollama pull llama3
Additional Information
Monitoring the Health of the instance
- Navigate to your Amazon EC2 console and verify that you're in the correct region.
- Choose Instance and select your launched instance.
- Select the server to display your metadata page and choose the Status checks tab at the bottom of the page to review if your status checks passed or failed.
Data Encryption
- This image does not provide encryption by default at the Operating System or Application level, customers are encouraged to enable EBS encryption during the Instance Launch: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/EBSEncryption.html
- EBS Encryption using the Default key enables key rotation
- More details: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/EBSEncryption.html#kms-key-rotation
- Using EBS encryption, the decryption is done automatically when using the instance.
- Customer data can be saved anywhere in the instance, however it is a good practice to save user data (including sensitive data) in the /home/<user-name> directory.
Resources
Vendor resources
Support
Vendor support
Arara Solutions provides limited support covering the launch and use of the instance, see details on http://arara.solutions/support-plans/ Contact us via http://arara.solutions/support/ or support@arara.solutions and mention product: Ubuntu 26.04 with Ollama & DeepSeek R1 7B by Arara Solutions
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Run DeepSeek and local models in your AWS account. This product has charges associated with it for a GPU backed private AI workspace and seller support.
This product has charges associated with it for seller support. Run & Manage latest LLMs locally, privately, securely and cost-effectively without any vendor lock-in.
This VM solution comes pre-loaded with LLaMA, Mistral, Gemma, DeepSeek, & Qwen models along with Open-WebUI as an intuitive UI to interact with the LLMs and Ollama to install new models as needed.
This product includes additional charges for seller support. Deep Seek AI is a cutting-edge artificial intelligence platform designed to power advanced data analysis and insights at scale. Root partition and filesystem automatically expands at boot for volumes larger than 8 GiB, for seamless scalability. Preconfigured with Cloud-init and ENA support for enhanced network performance. With robust machine learning models, real-time analytics, and intuitive dashboards, Deep Seek AI helps businesses uncover hidden patterns, optimize processes, and make data-driven decisions effortlessly. Ideal for industries like finance, healthcare, and e-commerce, it seamlessly integrates with your existing cloud infrastructure, delivering scalable, secure, and actionable intelligence. Accelerate your innovation journey with Deep Seek AI, where complexity meets clarity
This product has charges associated with it for seller support. Run & Manage latest LLMs locally, privately, securely and cost-effectively without any vendor lock-in. This VM solution comes with GPU support , pre-loaded with LLaMA, Mistral, Gemma, DeepSeek, & Qwen models along with Open-WebUI as an intuitive UI to interact with the LLMs and Ollama to install new models as needed.
This product has charges associated with it for seller support. DeepSeek-R1 with Open WebUI is a powerful Amazon Machine Image (AMI) designed for advanced web data extraction and analysis. Built to seamlessly integrate with the EC2 cloud, it allows users to leverage a robust framework for developing and deploying web scraping applications. Featuring an intuitive Ideal for data scientists and developers, DeepSeek-R1 is well-suited for use cases ranging from competitive analysis and market research to academic studies and machine learning model training. DeepSeek R1 with Open WebUI is an open-source AI model offering advanced reasoning capabilities, comparable to OpenAI's GPT series.
This product has charges associated with it for the provision and deployment of the application and AMI support. Unlock the full potential of DeepSeek AI by self hosting it on your own infrastructure. This powerful large language model offers advanced reasoning, coding, and mathematical capabilities, making it an ideal solution for AI enthusiasts, developers, and enterprises looking for privacy, speed, and scalability without reliance on third-party providers.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.