FICHA · AUR

ollama-for-amd

Create, run and share large language models (LLMs) with ROCm, patched for AMD GPUs

  • llm-runtime
  • CLI
  • SERVICE
  • AI
  • Launchable
  • Background service
official+codex · reviewed · Jun 2, 2026 description in en

Description

Local language models can run with ROCm support patched for AMD GPUs. This helps users test AI inference on AMD hardware when the standard build does not fit their setup.

It is an Ollama variant for GPU acceleration. Check ROCm compatibility, GPU memory, model licenses, and prompt privacy before production use.

How to run

ollama

Commands: ollama

Permissions

Permissions not analysed for this source yet.