FICHA · AUR

llama.cpp-vulkan-gemma4

Port of Facebook's LLaMA model in C/C++ (Vulkan, Gemma 4 model fixes)

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

Description

Vulkan-based local inference can include fixes aimed at Gemma 4 model workflows.

This package is useful for users who specifically need llama.cpp Vulkan behavior adjusted for Gemma 4. It is a specialized inference variant, not the Gemma model itself.

Specialized builds can become outdated as upstream changes. Verify model compatibility before long runs.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.