Sold by: RELEVANCE LAB
Deployed on AWS
Private LLM Server powered by Ollama for Amazon Linux 2023. Preconfigured AI environment with NVIDIA CUDA, JupyterLab, Docker, VS Code, PyTorch, TensorFlow, LangChain, and Hugging Face. Deploy private LLMs, build RAG applications, and accelerate Generative AI development on AWS.
Overview
Overview
Enterprise Private LLM Server with Ollama is a preconfigured Amazon Linux 2023 environment designed to accelerate Generative AI, machine learning, and data science workloads on AWS. The solution combines Ollama for local Large Language Model (LLM) deployment, GPU acceleration through NVIDIA CUDA, modern development tools, and industry-leading AI frameworks in a single ready-to-use platform.
Organizations can rapidly build, test, and deploy private AI assistants, Retrieval-Augmented Generation (RAG) applications, document intelligence solutions, and machine learning models without spending time configuring operating systems, drivers, development environments, and AI dependencies.
The platform is optimized for AWS deployments and provides a secure, scalable environment for developers, researchers, data scientists, and enterprise AI teams.
Key Features
Private LLM Deployment with Ollama Run open-source Large Language Models directly within your AWS environment using Ollama, enabling private AI workloads while maintaining control over data and infrastructure.
GPU-Accelerated AI Environment Preconfigured NVIDIA Driver, CUDA Toolkit, and cuDNN support accelerated model inference, fine-tuning, and machine learning workloads on AWS GPU instances.
Generative AI Development Stack Includes Ollama, Hugging Face Transformers, LangChain, LlamaIndex, FAISS, LoRA/PEFT, FastAPI, MLflow, MONAI, and Weights & Biases for developing modern AI applications.
Retrieval-Augmented Generation (RAG) Ready Build enterprise search, document intelligence, knowledge management, and conversational AI solutions using vector search and retrieval frameworks.
Development and Collaboration Tools Includes Visual Studio Code, PyCharm Community Edition, RStudio Desktop, Jupyter Notebook, and JupyterLab for end-to-end AI development.
Containerized AI Workloads Docker and Docker Compose are preconfigured for deploying scalable AI applications and microservices.
AWS-Native Integration Compatible with Amazon Bedrock, Amazon SageMaker, Amazon OpenSearch Service, Amazon S3, and other AWS services commonly used in AI and machine learning architectures.
Secure Remote Access Amazon NICE DCV provides high-performance remote desktop access for development, experimentation, and visualization workloads.
Technical Details
Operating System Amazon Linux 2023
Remote Access Amazon NICE DCV
Browsers and Utilities Google Chrome Git AWS CLI 7-Zip
Programming Languages Python 3.x R
Development Tools Visual Studio Code PyCharm Community Edition RStudio Desktop
Notebook Environments Jupyter Notebook JupyterLab
Containerization Docker Docker Compose
AI and Generative AI Frameworks Ollama Hugging Face Transformers LangChain LlamaIndex FAISS LoRA/PEFT FastAPI MLflow MONAI Weights & Biases
Machine Learning and Data Science Libraries PyTorch TensorFlow Scikit-learn PySpark Dask Vowpal Wabbit
Productivity Tools LibreOffice
GPU Software Stack NVIDIA Driver CUDA Toolkit cuDNN
Highlights
- Private LLM Deployment with Ollama Run open-source Large Language Models securely within your AWS environment using Ollama, enabling private AI workloads without relying on external AI services.
- 2. GPU-Ready Generative AI Platform Preconfigured with NVIDIA Drivers, CUDA Toolkit, cuDNN, and leading AI frameworks to accelerate model inference, experimentation, and AI application development.
- 3. Build AI Applications in Minutes Includes JupyterLab, VS Code, Docker, LangChain, LlamaIndex, FAISS, and machine learning frameworks, allowing teams to rapidly develop RAG solutions, AI assistants, and data science workloads.
Details
Sold by
Categories
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
AmazonLinux 2023
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
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Vendor refund policy
NA
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
NA
Additional details
Usage instructions
Quick Usage Summary
-
Subscribe to the AWS Marketplace product and launch an EC2 instance.
-
For optimal AI and LLM performance, use a GPU-enabled instance such as: g4dn.xlarge g4dn.2xlarge g4dn.4xlarge g5.xlarge g5.2xlarge or larger.
-
Configure a root EBS volume of at least 100 GB. A minimum of 200 GB is recommended for AI models, datasets, and development workloads.
-
Connect to the instance using Amazon NICE DCV or SSH.
-
Verify the installed AI environment:
python3 --version docker --version ollama --version
Connect via NICE DCV
- Open a browser and navigate to:
https://PUBLIC_DNS_NAME:8443
-
Log in using your configured Linux user credentials.
-
Access the Amazon Linux desktop environment.
-
Launch Visual Studio Code, JupyterLab, RStudio Desktop, Google Chrome, or Terminal from the desktop.
Note: Ensure TCP port 8443 is allowed in the EC2 Security Group.
Using Ollama
-
Open a terminal window.
-
Verify Ollama installation:
ollama --version
- List available models:
ollama list
- Run a model:
ollama run llama3
- Download additional models:
ollama pull mistral
ollama pull qwen3
ollama pull deepseek-r1
- Access the Ollama API endpoint locally:
Using JupyterLab
-
Launch JupyterLab from the desktop menu.
-
Create a new notebook.
-
Import and use preinstalled AI and machine learning libraries.
-
Develop AI applications, machine learning workflows, and data science projects.
Using Development Tools
-
Launch Visual Studio Code, PyCharm Community Edition, or RStudio Desktop.
-
Create or open existing projects.
-
Build AI assistants, RAG applications, machine learning models, APIs, and analytics solutions.
Using Docker
- Verify Docker installation:
docker --version
- Start containerized applications:
docker compose up -d
- Deploy scalable AI services and development environments.
Preinstalled AI Frameworks
Ollama Hugging Face Transformers LangChain LlamaIndex FAISS PyTorch TensorFlow FastAPI MLflow MONAI LoRA/PEFT
AWS Service Integration
This environment can be integrated with:
Amazon Bedrock Amazon SageMaker Amazon OpenSearch Service Amazon S3 AWS IAM
These services can be used together with Ollama and the preinstalled AI frameworks to build enterprise-grade Generative AI solutions on AWS.
Support
Vendor support
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 is a repackaged software product wherein additional charges apply for seller maintenance.
Deploy a powerful, self-hosted AI server supporting multiple LLMs (including Deepseek) via Open WebUI and Ollama. Streamline AI inference, customization, and local model management in a scalable AWS environment.
Optick Instant AI Ready VS Code Server is a turnkey, cloud based IDE preconfigured with multi model AI support; empower your team to code smarter using GPT4, CodeLlama, and any LLM of your choice, directly in the browser.
This product has charges associated with it for seller support. Open WebUI is a web-based interface that allows you to run and interact with large language models (LLMs) locally or on a server.
Buoyant Enterprise for Linkerd is a production-ready distribution of the Linkerd service mesh that provides critical security and reliability features to Kubernetes applications.
The Splunk Enterprise AMI accelerates the speed at which organizations deploy Splunk Enterprise in AWS..
NVIDIA AI Enterprise is an end-to-end, cloud-native software platform that accelerates data science pipelines and streamlines development and deployment of production-grade AI applications, including generative AI.
Upgrade open-source Grafana with premium data sources, access control, reporting and other functionality, as well as support and professional services from Grafana Labs, the creators of Grafana. This Grafana Enterprise offering is for customers who want to self-manage Grafana on AWS.
Enterprise security solutions powered by TrendAI™ (a business unit of Trend Micro) to help protect users, data, and workloads. Contact us today to tailor a solution for your needs!
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.