FICHA · AUR

llama.cpp-opencl

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

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

Description

OpenCL GPU acceleration can be used for local LLM inference on supported devices.

This package is useful for users who need the OpenCL backend for llama.cpp instead of CUDA, ROCm, or CPU-only execution. It is an inference build variant.

OpenCL behavior varies by driver and hardware. Test model loading and performance before depending on it.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.