FICHA · AUR

ollama-cuda13-bin

Create, run and share large language models (LLMs) with CUDA 13

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

Description

Local language models can run with NVIDIA CUDA 13 acceleration on compatible systems. This helps users test newer CUDA stacks for faster AI inference.

It is an Ollama binary variant for CUDA 13. Confirm driver support, GPU memory, model licensing, and prompt privacy before relying on it for real workloads.

How to run

ollama

Commands: ollama

Permissions

Permissions not analysed for this source yet.