Base
Hardened build
minimal ports, security patches applied at build time
llama.cpp
Azure
Applications
1 variation
llama.cpp Server, an efficient local inference engine for open LLMs, ready to serve models from first boot.
Variations
This product is available in the build below. Open it for the operating system, cloud and version detail, or read its deployment guide.
| Product | Cloud | Operating system | Version | |
|---|---|---|---|---|
| llama.cpp Server on Ubuntu 24.04 | Azure | Ubuntu 24.04 | Standard | View · Guide |
Overview
llama.cpp is a high efficiency inference engine that runs open large language models on CPU and GPU hardware, exposing an OpenAI compatible server. It is used to host and serve local LLMs with minimal overhead.
Why the cloudimg image
cloudimg ships the llama.cpp server hardened and fully patched, preconfigured so the inference endpoint is ready on first boot. 24/7 support is included with every image.
Common uses
- Local LLM inference
- Private model serving
- OpenAI compatible endpoints
More in Applications
Actual Budget
Applications
Actual Budget, the local first envelope budgeting app, running as your own private sync server the moment it boots.
Admidio
Applications
Admidio, the open source membership management platform for clubs, associations and non profit organisations, configured
Ai
Aim
Applications
Aim, an open source experiment tracker for machine learning, hardened and ready on Ubuntu 24.04.
Ant Media Server
Applications
Ant Media Server Community Edition, the open source real time WebRTC and RTMP streaming engine, with a per VM admin pass
Apache Answer
Applications
Apache Answer, an open source question and answer knowledge base, fully initialised and ready with no setup wizard.
Af
Apache Fineract
Applications
Apache Fineract, an open source core banking platform, ready for financial services workloads on first boot.