Sold by: Meetrix.io
Deployed on AWS
Free Trial
LocalAI is an open source, self-hosted AI engine that runs large language models, embeddings, speech, and image models on your own server, with no GPU required. Its OpenAI-compatible API lets existing SDKs and tools work by changing only the base URL, and a built-in web UI lets you chat and install models from a gallery of 1,900+ models in one click. This preconfigured AMI deploys LocalAI v4.11.0 with the Qwen3-4B-Instruct chat model preloaded, automatic CPU or NVIDIA GPU detection at every boot, API key authentication, an Nginx reverse proxy, and automatic Let's Encrypt SSL. Ideal for developers, startups, SaaS platforms, and enterprises that want a private, cost-controlled AI API where prompts and data never leave their own infrastructure.
Overview
LocalAI is an open source, self-hosted AI engine with an OpenAI-compatible API. Run large language models, embeddings, speech-to-text, text-to-speech, and image generation models on your own server, then point your existing SDKs and tools at your own endpoint. This preconfigured LocalAI AMI is built for developers, startups, SaaS platforms, and enterprises that want a private AI API without per-token fees or sending data to third parties. It launches on AWS in minutes, runs on regular CPU instances or NVIDIA GPU instances, and answers chat requests as soon as the stack is up.
LocalAI Step by step Installation Guide: https://meetrix.io/blogs/localai-developer-guide/
For custom projects of your choice with personalized support, contact us at https://meetrix.io/contact-us
Instant Deployment: Launch a fully configured LocalAI server in minutes using a ready-to-use AMI and CloudFormation template, with Docker, an Nginx reverse proxy, and Let's Encrypt SSL set up for you. The model is read from disk and warmed up on first boot, so the first request answers right away.
Drop-In API Replacement: Use the /v1 endpoints for chat completions, embeddings, audio, and images with existing SDKs, frameworks, and tools by changing only the base URL and API key. Interactive API documentation is available at /swagger.
CPU or NVIDIA GPU from One AMI: The instance checks for an NVIDIA GPU at every boot and starts the matching LocalAI image. Run on low-cost CPU instances such as t3a.xlarge with no GPU required, or on g4dn, g5, g6, and g6e GPU instances for around 30x faster responses. Stop the instance, change its type between CPU and GPU, and start it again with no other changes.
Preloaded Chat Model: Qwen3-4B-Instruct-2507 (Apache-2.0, Q4_K_M GGUF) is installed with llama.cpp CPU and CUDA backends, so you can chat in the web UI or call the API immediately with no downloads. It answers directly without a thinking phase, which keeps replies fast on CPU.
Model Gallery and Web UI: Chat with your models, browse a gallery of 1,900+ models, and install LLMs, embedding, speech-to-text, text-to-speech, and image generation models in one click from the built-in web interface.
API Key Authentication: The API key you choose at launch protects every API route and the web UI login, and is sent as a standard bearer token with each request.
Secure HTTPS Access: Nginx serves HTTPS with an automatic Let's Encrypt certificate through the Route 53 DNS challenge and keeps long requests and token streams open for slow CPU inference, while SSH is restricted to your chosen IP range.
Private and Self-Hosted: Prompts, responses, and model files stay on your own EC2 instance inside your own VPC, with no per-token fees and full control over data residency and cost.
Version: v4.11.0
Operating System: Ubuntu 26.04
LocalAI gives developers, startups, SaaS platforms, and enterprises a flexible, private AI engine for chatbots, assistants, retrieval-augmented generation, document processing, and AI-powered product features, without per-token pricing or vendor lock-in. Deploy your own AI API in minutes on CPU or GPU and keep full ownership of your models and data. LocalAI Step by step Installation Guide: https://meetrix.io/blogs/localai-developer-guide/
Highlights
- Drop-In AI API on Your Own Server: Serve chat, embeddings, speech, and image models through a standard /v1 REST API that works with popular AI SDKs and tools by changing only the base URL, protected by an API key you choose at launch.
- CPU or GPU, Detected Automatically: Run on low-cost CPU instances with no GPU required, or on NVIDIA g4dn, g5, g6, and g6e instances for around 30x faster responses. The matching image starts at every boot, so switching instance types needs no changes.
- Ready to Chat in Minutes: A preloaded instruct chat model, a web UI with one-click installs from a gallery of 1,900+ models, an Nginx reverse proxy, and automatic SSL let you start chatting or calling the API as soon as the stack is up.
Details
Sold by
Delivery method
Delivery option
LocalAI Deployment with CPU and NVIDIA GPU LLM Inference
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
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 |
|---|---|
t3.xlarge | $0.029 |
t3.large | $0.024 |
t3.2xlarge | $0.029 |
t3a.large | $0.024 |
t3a.xlarge | $0.029 |
t3a.2xlarge | $0.029 |
m5.large | $0.024 |
m5.xlarge | $0.029 |
m5.2xlarge | $0.029 |
m5a.large | $0.024 |
Vendor refund policy
We do not currently support refunds, but you can cancel at any time.
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
LocalAI Deployment with CPU and NVIDIA GPU LLM Inference
This deployment launches LocalAI on a single EC2 instance using a CloudFormation template. The stack creates a VPC with a public subnet, the instance with a 60 GiB gp3 root volume and an Elastic IP, a security group that opens HTTP and HTTPS and restricts SSH to your chosen IP range, and an IAM role that allows Route 53 DNS validation for Let's Encrypt SSL. The same AMI runs on CPU instances and on NVIDIA g4dn, g5, g6, and g6e GPU instances: at every boot the instance checks for an NVIDIA GPU and starts the LocalAI v4.11.0 CUDA 13 image with GPU passthrough, or the CPU image when no GPU is found. On first boot, UserData sets your API key, requests the SSL certificate, reads the preloaded Qwen3-4B-Instruct model and llama.cpp backend from disk, starts LocalAI with Docker Compose, and warms up the model so the first request answers right away. Nginx serves HTTPS and proxies to LocalAI with long timeouts and streaming for slow CPU inference. Allow about 5 minutes on CPU or 8 minutes on GPU for first boot, then open the URL shown in the stack Outputs and log in with your API key to chat in the web UI, install more models from the gallery, or call the API at https:///v1. This architecture provides a private, cost-controlled AI API with simple management on CPU or GPU.
CloudFormation Template (CFT)
AWS CloudFormation templates are JSON or YAML-formatted text files that simplify provisioning and management on AWS. The templates describe the service or application architecture you want to deploy, and AWS CloudFormation uses those templates to provision and configure the required services (such as Amazon EC2 instances or Amazon RDS DB instances). The deployed application and associated resources are called a "stack."
Version release notes
Release Notes First Release
Additional details
Usage instructions
"Click the ""Continue to Subscribe"" button. After subscribing, you will need to accept the terms and conditions. Click on ""Accept Terms"" to proceed. Please wait for a few minutes while the processing takes place. Once it's completed, click on ""Continue to Configuration"".
IAM Role is set up and configured with the necessary permissions to assume the role for the LocalAI service. The IAM Policy is created and responsible for access Route53 and create Letsencrypt SSL certificates and backing up data to the S3 bucket.
Access the application via a browser at http://<your domain name> or http://<Public IPv4 address>. Product will try to create SSL certificate when its deploying, if domain hosted on route53. If the automatic SSL creation unsuccessful then you have to point domain name into server ip, ssh into server and run /root/certificate_generate_standalone.sh. Admin email using for SSL generation."
Resources
Vendor resources
Support
Vendor support
Please contact us through aws@meetrix.io . Please allow up to 12 hours for our support team to address your request.
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
Preconfigured LocalAI virtual machine for running AI models on your own infrastructure. Unified platform for AI Chat, image and voice generation, LLMs and embeddings with OpenAI API compatibility.
Available in both CPU and GPU configurations.
REQUIRES PRIVATE OFFER
To purchase LiteLLM Enterprise Self-Hosted, please reach out to sales@berri.ai for a Private Offer.
LiteLLM is an OpenAI compatible Proxy Server (LLM Gateway) to call 2,000+ LLM APIs using the OpenAI format Bedrock, Huggingface, VertexAI, TogetherAI, Azure OpenAI, OpenAI, etc. Get started with Opensource LiteLLM here: https://github.com/BerriAI/litellm (40,000+ Github Stars)
vLLM is a high-throughput inference and serving engine for large language models. This preconfigured Amazon Machine Image deploys a production-ready vLLM server with an OpenAI-compatible API on a GPU EC2 instance, so you can serve open-source models such as Llama, Qwen, Mistral, and Gemma from your own infrastructure in minutes. It ships with NVIDIA drivers, the NVIDIA Container Toolkit, an Nginx reverse proxy, and automatic Let's Encrypt SSL, and uses PagedAttention and continuous batching to maximize tokens per second and GPU utilization. Point any OpenAI SDK at your endpoint and start generating.
Self-hosted GLM 5.3 Flash served via SGLang with an OpenAI-compatible API. Weights are fetched from public S3 at first boot and an API key is auto-generated.
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.