FICHA · AUR

llama.cpp-openvino

Port of Facebook's LLaMA model in C/C++(with OpenVINO Backend support)

  • llm-inference-tool
  • CLI
  • Dev
  • Launchable
  • Runs in terminal
official+codex · reviewed · Jun 2, 2026 description in en

Description

OpenVINO acceleration can support local LLM inference on compatible Intel-oriented hardware.

This package is useful for users who want llama.cpp with the OpenVINO backend. It provides inference tooling, not model weights or a chat UI.

Acceleration stacks can depend on exact runtime versions. Verify device support and protect prompts processed locally.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.