FICHA · AUR

llama.cpp-vulkan-bin

LLM inference in C/C++ (with Vulkan GPU optimizations) (precompiled Linux binaries)

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

Description

Precompiled Vulkan acceleration makes local LLM inference easier to try on supported GPUs.

This binary package is useful for users who want ready llama.cpp executables with Vulkan optimizations. It includes inference tools, not model files.

Vulkan GPU inference depends on drivers and can use substantial VRAM. Protect local server ports and private prompts.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.