Sold by: ProvenCloud
Deployed on AWS
Free Trial
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use Ollama 0.40.13 AI server with Open WebUI v0.12.5. Chat with open AI models privately in your browser, with a model ready to use, documents and chat history kept on your own instance and no shared default password.
Overview
Ollama runs open large language models on your own server, and Open WebUI gives them a familiar chat interface in the browser, with accounts, chat history, document upload for questions over your own files, and model switching. Your prompts, documents and conversations stay on your instance and are never sent to an outside AI service. Teams, schools and businesses use it for private AI chat without per-user subscriptions. A small open model is already installed, so you can start chatting a few minutes after launch.
What is included: Ollama 0.40.13 and Open WebUI v0.12.5, unmodified upstream releases pinned to exact versions, running in Docker 29.9 with Compose, the qwen2.5:1.5b model (Apache-2.0) already downloaded, Apache on port 80 with the websocket support Open WebUI needs, and Webmin 2.670 for server administration, on Ubuntu 24.04 LTS with all security updates. Security is on by default: no account ships in the image. The first person to sign up becomes the administrator and public sign-up then closes; if it is reopened, newcomers wait for approval. Every instance creates its own Open WebUI signing key on first boot. The Ollama API and Open WebUI's own port listen only on the instance itself, behind Apache, and SSH accepts key-based login only. Helper scripts pull and remove models and back up accounts, chats and documents. Models run on CPU out of the box; a 7B model needs about 8 GB of memory, and GPU instances need the NVIDIA driver added.
What you get on top of the free software: a pre-built and tested image that is ready in minutes, a unique security setup for every server, simple scripts for changing passwords, regular image updates, and help by email whenever you need it. Ollama is open source software licensed under MIT, Open WebUI under its own BSD-3-Clause based licence with its branding kept intact, and the bundled Qwen2.5 1.5B model under Apache-2.0. Ollama and Open WebUI are trademarks of their respective owners. This image is an independent build by ProvenCloud, not an official distribution of either project.
Highlights
- Private AI chat: prompts, uploaded documents and chat history stay on your instance and are never sent to an outside AI service. No API key or per-user AI subscription is needed.
- Ready on first visit: the qwen2.5:1.5b model is already downloaded, so you can chat within minutes, and one command adds bigger open models such as Llama, Qwen, Gemma or Mistral.
- Secure by default: no account ships in the image, the first person to sign up becomes the administrator and sign-up then closes, and the Ollama API is reachable only from the instance itself.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
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
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
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 |
|---|---|
t3a.xlarge Recommended | $0.05 |
c3.2xlarge | $0.08 |
c3.4xlarge | $0.08 |
c3.8xlarge | $0.08 |
c4.2xlarge | $0.08 |
c4.4xlarge | $0.08 |
c4.8xlarge | $0.08 |
c5.12xlarge | $0.08 |
c5.2xlarge | $0.08 |
c5.4xlarge | $0.08 |
Vendor refund policy
Software charges are billed hourly, only while your instance runs. You can stop charges at any time by terminating the instance or cancelling your subscription. Charges already incurred are not refundable.
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
Latest stable release on AWS Marketplace.
Ollama 0.40.13 and Open WebUI v0.12.5 (pinned upstream images) in Docker 29.9 with the qwen2.5:1.5b model, Apache and Webmin 2.670 on Ubuntu 24.04 LTS with all security updates.
No account ships in the image; every instance creates its own Open WebUI signing key on first boot, and the Ollama API listens only on the instance itself.
Includes helper scripts in /home/ubuntu/iscripts for changing passwords.
Additional details
Usage instructions
Once the instance is running, wait for the instance health checks to pass, then allow about four minutes for the first-boot setup to finish. Enter http://<instance-public-ip>/ into your browser. Open WebUI asks you to create an account: the first account created becomes the administrator, so create it straight away, and public sign-up then closes automatically.
A ready-to-use model (qwen2.5:1.5b) is already installed, so you can start chatting immediately. To add more models, connect over SSH and run sudo bash /home/ubuntu/iscripts/ai-model.sh pull <model>, for example llama3.2:3b; they appear in the model list without a restart. To back up accounts, chats and documents, run sudo bash /home/ubuntu/iscripts/ai-backup.sh. You can access the Webmin page at port 8000, so your URL will be http://<instance-public-ip>:8000 and use admin as username and your instance ID as password. You can also access your instance via SSH using the username ubuntu and your Amazon private key.
Required inbound ports: 22 (SSH), 80 (Open WebUI) and 8000 (Webmin). For security, allow ports 22 and 8000 only from your own IP address. Never open port 11434: the Ollama API has no authentication, and it listens only on the instance itself.
Your instance ID is shown in the EC2 console, for example i-0123456789abcdef0, all lowercase. It is used only for Webmin. To change the Webmin password, run sudo bash /home/ubuntu/iscripts/pass_webmin.sh.
Recommended size: t3a.xlarge (4 vCPU, 16 GiB) or larger. The bundled model answers in a few seconds on CPU; a 7B model needs about 8 GB of memory and runs more slowly on CPU. For larger models use a GPU instance and install the NVIDIA driver and container toolkit.
Resources
Support
Vendor support
Email: support@provencloud.io
Support page: https://www.provencloud.io/support
Hours: Monday to Friday, 10:00 to 19:00 IST (UTC+05:30)
Billing and refunds for this subscription are handled by AWS Marketplace.
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
This product has charges associated with it for support. Ollama is a cutting-edge AI tool that empowers users to set up and run large language models, such as Llama 2 and 3, directly on their local machines. This innovative solution caters to a wide range of users, from experienced AI professionals to enthusiasts, enabling them to explore natural language processing without depending on cloud-based services.
![MariaDB with phpMyAdmin on Ubuntu 24.04 LTS by ProvenCloud [IN]](https://d7umqicpi7263.cloudfront.net/img/product/19bd0105-bfaa-4197-91cf-b824fa63c88c.com/4c173b409be2aeb8869f955151e879be)
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use MariaDB 12.3 LTS database server with phpMyAdmin. Get a tuned, MySQL-compatible database for your applications in minutes, sized to your instance automatically, with unique passwords for every instance.
![LEMP Stack (Nginx, MySQL, PHP) on Ubuntu 24.04 LTS by ProvenCloud [IN]](https://d7umqicpi7263.cloudfront.net/img/product/70698a84-a1f5-4f78-bbce-020bf067544b.com/4c173b409be2aeb8869f955151e879be)
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use LEMP stack with Nginx, MySQL, PHP 8.5, phpMyAdmin and Webmin. Run fast PHP websites and apps from day one, with unique passwords for every instance.
![Moodle LMS on Ubuntu 24.04 LTS by ProvenCloud [IN]](https://d7umqicpi7263.cloudfront.net/img/product/2e1b5b75-f675-44aa-8c5c-184c3bcada1d.com/4c173b409be2aeb8869f955151e879be)
This is a repackaged open source software product wherein additional charges apply for a secure, ready-to-use Moodle 4.5 LTS learning platform. Run online courses, quizzes, assignments and virtual classes on your own server, with unique passwords for every instance.
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.