FICHA · MANJARO

ollama-vulkan

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

  • Service
  • COMMAND-LINE
  • LOCAL-SERVICE
  • AI-MODELS
  • Launchable
  • Runs in terminal
  • Background service
official+codex · reviewed · May 28, 2026 description in en

Description

Provides Ollama with Vulkan support for running large language models through compatible GPU drivers. Vulkan acceleration can broaden hardware support beyond a single vendor stack.

Use it when CUDA or ROCm is not the right path and the system has suitable Vulkan support. Performance and compatibility depend on the driver, GPU, model size, and memory available.

How to run

ollama

Commands: ollama

Permissions

Permissions not analysed for this source yet.