llama.cpp Server on Ubuntu 24.04

Applications

Overview

Self-hosted llama.cpp Server on Ubuntu 24.04 LTS by cloudimg. Upstream llama.cpp's own single-binary CPU inference engine - a built-in browser chat UI plus an OpenAI-compatible REST API (/v1/chat/completions), no GPU required. Bundled with a small redistributable demo model (Qwen2.5-1.5B-Instruct, Apache-2.0) ready to chat with on first boot. nginx on port 80 with a per-VM HTTP Basic Auth password generated on first boot. MIT licensed.

Description

llama.cpp is the reference CPU-first inference engine for GGUF-quantized large language models - no GPU required. This appliance installs upstream's own llama-server binary (the official prebuilt CPU release, not a third-party wrapper), which serves two things from a single process: a built-in browser chat UI and an OpenAI-compatible REST API (/v1/chat/completions, /v1/completions, /v1/models). llama-server has no login system of its own, so the cloudimg image locks it down for a marketplace appliance: llama-server is bound to loopback only, and nginx does all customer-facing work on port 80 - a per-VM HTTP Basic Auth gate protects both the chat UI and the API, and an unauthenticated /healthz endpoint serves load balancer probes. A small, genuinely redistributable demo model - Qwen2.5-1.5B-Instruct, Apache License 2.0 - is pre-downloaded onto a dedicated data disk so you can start chatting or calling the API within a minute of first boot, with no internet access required at runtime. Swap in a larger GGUF model at any time by dropping a new file onto the data disk and editing the systemd unit - documented step by step in the user guide. Licensing: MIT (llama.cpp) + Apache-2.0 (bundled demo model), FREE - no per-request or per-seat fee. Backed by 24/7 cloudimg support.

Key Features

  • llama.cpp build b9937 (MIT) official prebuilt CPU release - single binary serves both a built-in chat UI and the OpenAI-compatible REST API (/v1/chat/completions, /v1/models), no GPU required
  • Bundled demo model Qwen2.5-1.5B-Instruct (Q4_K_M GGUF, Apache-2.0, ~1.04 GiB) pre-loaded on a dedicated data disk - chat or call the API within a minute of first boot, no internet needed at runtime
  • nginx on port 80 fronts both the chat UI and API behind a per-VM HTTP Basic Auth password generated on first boot; llama-server itself bound to loopback only; unauthenticated /healthz for load balancer probes

Related Technologies

llama.cpp llm inference self-hosted ai openai compatible api gguf chat ui cpu inference qwen2.5 ubuntu 24.04 private llm

Deploy on Azure

Launch this pre-configured VM on Azure with 24/7 support from cloudimg.

View on Azure Marketplace

24/7 Support Included

Email: support@cloudimg.co.uk

Phone: (+44) 0333 006 4730

Product Details

Category
Applications
Support
24/7, 365 days/year
Platform
Microsoft Azure
Last Updated
2026-07-09