FICHA · MANJARO

fastflowlm

Run LLMs on AMD Ryzen AI NPUs

  • cli
  • CLI
  • Launchable
  • Runs in terminal
official+codex · reviewed · May 27, 2026 description in en

Description

A tool for running large language models on AMD Ryzen AI NPUs. It is aimed at users and developers experimenting with local AI acceleration on supported AMD hardware.

Use it only if your system has a compatible Ryzen AI NPU and the required driver stack. Model support, memory limits, and performance depend heavily on hardware and runtime configuration.

How to run

fastflowlm

Commands: fastflowlm

Permissions

Permissions not analysed for this source yet.