FICHA · AUR

ollama-rocm-git

Create, run and share large language models (LLMs) with ROCm

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

Description

Local language models can use ROCm for acceleration on compatible AMD GPUs. This helps users run AI models locally with better performance than CPU-only inference.

It is an Ollama development package for ROCm systems. Review driver support, model size, disk usage, and prompt privacy before use.

How to run

ollama

Commands: ollama

Permissions

Permissions not analysed for this source yet.