FICHA · AUR

llama.cpp-gfx1151

Port of Facebook's LLaMA model in C/C++ (Optimized for gfx1151, ROCm + Vulkan)

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

Description

Specific AMD gfx1151 hardware can use a ROCm and Vulkan optimized llama.cpp build.

This package is useful for users whose GPU matches that target and who want local LLM inference performance. It is a hardware-specific build variant, not a general model package.

Wrong GPU targets can waste time or fail to run. Confirm the GPU architecture and driver stack before installing.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.