FICHA · AUR

localai-git-cuda

Self-hosted OpenAI API alternative - Open Source, community-driven and local-first. (with CUDA support)

  • ai-server
  • CLI
  • Web
  • NETWORK
  • Launchable
  • Runs in terminal
  • Background service
official+codex · reviewed · Jun 2, 2026 description in en

Description

Current LocalAI server code can use CUDA acceleration for self-hosted AI workflows.

This Git package is useful for developers with compatible NVIDIA GPUs who need the CUDA-enabled LocalAI variant. It provides server infrastructure, not models.

CUDA AI servers can consume large VRAM and expose local APIs. Verify drivers, restrict ports, and protect prompts.

How to run

local-ai

Commands: local-ai

Permissions

Permissions not analysed for this source yet.