aws-samples/sample-ollama-server
Ollama on GPU EC2 instance with Open WebUI web interface and Bedrock access
This project helps individuals and teams set up their own private environment for experimenting with and running large language models (LLMs). It provides a web interface where you can interact with various LLMs, including popular open-source models and Amazon Bedrock models. This is ideal for researchers, developers, or data scientists who need a secure, powerful platform to explore generative AI applications.
Use this if you need a dedicated, high-performance environment to run and interact with large language models, including both open-source and proprietary options like Amazon Bedrock, without managing complex infrastructure yourself.
Not ideal if you prefer using publicly available LLM services directly or if your primary need is basic text generation that doesn't require a dedicated GPU server.
Stars
25
Forks
2
Language
—
License
MIT-0
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/aws-samples/sample-ollama-server"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
containers/ramalama
RamaLama is an open-source developer tool that simplifies the local serving of AI models from...
av/harbor
One command brings a complete pre-wired LLM stack with hundreds of services to explore.
RunanywhereAI/runanywhere-sdks
Production ready toolkit to run AI locally
runpod-workers/worker-vllm
The RunPod worker template for serving our large language model endpoints. Powered by vLLM.
foldl/chatllm.cpp
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)