FICHA · AUR

ik-llama.cpp-vulkan

llama.cpp fork with additional SOTA quants and improved performance (Vulkan Backend)

  • local-llm-inference-tool
  • CLI
  • TERMINAL
  • AI
  • Launchable
  • Runs in terminal
official+codex · reviewed · Jun 1, 2026 description in en

Description

Local large-language-model inference can use Vulkan-capable GPUs with extra quantization formats.

It is useful for users running offline AI models across a wider range of graphics hardware. Local models can still process sensitive text and may generate wrong output, while Vulkan builds require compatible drivers.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.