> Source: https://meetrix.io/store/localai/ > Markdown copy of that page. Cite the URL above, not this file. [Store](https://meetrix.io/store/) LocalAI Open-source AI engine # Self-hosted LocalAI on AWS and Google Cloud Run language, image and audio models on your own AWS instance or Google Cloud VM with LocalAI, the open-source engine with an OpenAI-compatible API. The pre-configured image runs on CPU or GPU, protects the web UI and the API with your own API key, and comes with a model ready to chat with. [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-25t7st4jas56g)[ Launch on Google Cloud](https://console.cloud.google.com/marketplace/product/meetrix-public/localai-openai-alternative) - Runs on CPU or GPU - OpenAI-compatible API - Model pre-installed ![LocalAI server deployed on AWS and Google Cloud by Meetrix](https://meetrix.io/assets/store/localai/localai.webp) ## What is LocalAI? LocalAI is an open-source, MIT-licensed AI engine that runs language, vision, voice and image models on your own hardware, with no GPU required. Its OpenAI-compatible API means code written for the OpenAI SDK works with a change of base URL, and its web UI lets you chat with models and install new ones from a gallery. It suits teams that want text, image and audio models behind one private API. - ### OpenAI-compatible Code written for the OpenAI SDK works with a change of base URL. - ### Text, image and audio Chat, embeddings, image generation, speech-to-text and text-to-speech. - ### No GPU required Runs on CPU; an NVIDIA GPU makes it faster. - ### Model gallery Install models from the gallery or import them from Hugging Face. - ### Web UI built in Chat with models and manage them in the browser. - ### Agents and MCP Model Context Protocol support and built-in agents with tool use. ## What's in the Meetrix LocalAI image The image is ready to use the moment the deployment finishes: LocalAI is installed, a model is loaded, and access is locked behind the API key you choose at launch. - LocalAI in Docker on Ubuntu 26.04 (4.11.0 on AWS, 4.12.1 on Google Cloud) - qwen3-4b-instruct pre-installed and ready to chat with - One image for CPU and NVIDIA GPU, detected at every boot - API key sign-in for the web UI and the API - Let's Encrypt SSL, set up automatically or with one script - Email support from Meetrix at aws@meetrix.io or support@meetrix.io ## How to set up a self-hosted LocalAI server 1. ### Choose CPU or GPU On AWS, t3a.xlarge runs LocalAI on CPU and g4dn.xlarge adds an NVIDIA T4. On Google Cloud, e2-standard-4 runs on CPU and the g2 types add an NVIDIA L4. GPUs often need a quota increase first. 2. ### Launch it Launch the CloudFormation stack from AWS Marketplace, or fill in the Google Cloud Marketplace deployment form, with your domain and an API key of your choice. 3. ### Point your domain Add an A record for the server's public IP. SSL is set up automatically when it can be, and a certificate script on the server covers the rest. 4. ### Sign in and call the API Sign in to the web UI with your API key, then point any OpenAI client at https://your-domain/v1. ## Choose your cloud ### LocalAI on AWS An AMI on AWS Marketplace, launched on a CPU or GPU instance in your own AWS account with a CloudFormation stack. Deploys with CloudFormation Recommended size t3a.xlarge (CPU) or g4dn.xlarge (GPU) Ready in 5-10 minutes #### Setup guides - [**Developer guide** CPU or GPU, models, API, SSL](https://meetrix.io/blogs/localai-developer-guide/) [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-25t7st4jas56g) ### LocalAI on Google Cloud The same engine as a Google Cloud Marketplace image, deployed on a CPU or NVIDIA L4 GPU VM in your own GCP project. Deploys with Marketplace deployment form Recommended size e2-standard-4 (CPU) or g2-standard-8 (L4 GPU) Free trial 5 days, up to USD 50 licence credit #### Setup guides - [**Developer guide** CPU or L4 GPU, models, API, SSL](https://meetrix.io/blogs/localai-gcp-developer-guide/) [Launch on Google Cloud](https://console.cloud.google.com/marketplace/product/meetrix-public/localai-openai-alternative) ## LocalAI instance sizing The same image runs on both. Start on CPU to evaluate LocalAI or run small models, and move to a GPU when response times matter. | Cloud | Machine type | Hardware | Good for | | --- | --- | --- | --- | | AWS | t3a.xlarge | 4 vCPUs, 16 GB RAM | Trying LocalAI, small chat models, embeddings | | AWS | g4dn.xlarge | 4 vCPUs, 16 GB RAM, 1× NVIDIA T4 with 16 GB | 7B to 8B chat models, image generation, speech | | Google Cloud | e2-standard-4 | 4 vCPUs, 16 GB RAM | Trying LocalAI, light use, embeddings, batch jobs | | Google Cloud | g2-standard-8 | 8 vCPUs, 32 GB RAM, 1× NVIDIA L4 with 24 GB | Interactive chat, 7B to 14B models, image generation, speech | GPU instances use the On-Demand G and VT vCPU quota on AWS and the NVIDIA L4 GPU quota on Google Cloud, and both are often 0 in new accounts. ## LocalAI by Meetrix vs the OpenAI API | | LocalAI by Meetrix | OpenAI API | | --- | --- | --- | | Hosting | A server in your own AWS account or GCP project | OpenAI's platform | | Pricing model | Billed by the hour, no per-token fee | Mostly per token, with separate input and output rates | | Models | Open models from the LocalAI gallery or Hugging Face | OpenAI's own models | | Data | Prompts and outputs stay on your server | Not used for training by default; abuse monitoring logs kept up to 30 days | | Modalities | Text, embeddings, images, speech-to-text, text-to-speech | Text, embeddings, images, speech-to-text, text-to-speech, realtime voice | LocalAI speaks the OpenAI API, so moving code between the two is a change of base URL and API key. ## LocalAI FAQ What is LocalAI? An open-source, MIT-licensed engine for running AI models on your own hardware. It serves text, embedding, image and audio models through an OpenAI-compatible API, and includes a web UI for chatting with models and installing new ones. Is LocalAI free? LocalAI itself is free, open-source software under the MIT licence. You pay for the instance or VM and any charges shown on the Marketplace listing, but there is no per-token fee. The Google Cloud listing includes a 5-day free trial with up to USD 50 in licence credit. Do I need a GPU? No. The same image runs on CPU and GPU. On AWS, t3a.xlarge is the recommended CPU size and g4dn.xlarge adds an NVIDIA T4 with 16 GB of GPU memory. On Google Cloud, e2-standard-4 produces about 6-7 tokens per second with the pre-installed model, and the g2 types add an NVIDIA L4 with 24 GB for about 65 tokens per second. Which model comes with it? qwen3-4b-instruct is pre-installed, so you can chat with it as soon as you sign in. Install more from the gallery under Models in the web UI, choosing sizes that fit your instance. How do I sign in? Open the DashboardUrl from the CloudFormation Outputs tab on AWS, or your domain on Google Cloud, and enter the API key you set at launch. The same key is the bearer token for API requests. Is SSL set up for me? On AWS, LocalAI sets up SSL automatically when your domain is hosted on Route 53. On Google Cloud, it issues SSL on first boot if your domain already points at the VM. Otherwise, point an A record at the public IP and run the certificate script on the server, as the developer guides show. How do I upgrade? When a new version is on AWS or Google Cloud Marketplace, back up any models and configuration you need, delete the old deployment and launch the new version. How does it compare with the OpenAI API? Both speak the same API, so code moves between them with a change of base URL and key. LocalAI runs open models on a server in your own AWS account or GCP project, billed by the hour, while the OpenAI API runs OpenAI's models on its platform and bills mostly per token. ## Need a hand with LocalAI? We build and run self-hosted AI infrastructure for teams every day, from choosing between CPU and GPU to picking models and scaling. Tell us what you need. [Contact us](https://meetrix.io/contact-us/)