Find tools › Open-source projects › Keep data private

smolmaxxing

Open-source project · by hyperionaidev

Run text-generating AI models on low-power devices like TV boxes and old tablets by saving hardware memory.

Some setup

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Run AI models on older tablets and Android TV boxes
  • Stream model parameters from device storage to bypass memory limits
  • Benchmark custom compressed model formats on low-spec processors

How to start

  1. Download ready-made custom model files from Hugging Face

  2. Build or install the custom patched version of llama.cpp for your target device

  3. Follow the specific setup guides for your Android TV box or jailbroken iOS device

Good to know. Requires custom-patched builds of llama.cpp and specially reformatted model files; standard llama.cpp tools cannot open these models.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-13

More detail

smolmaxxing provides custom patches for llama.cpp that enable text-generating AI models to run on low-memory hardware like TV boxes and old tablets.

Most AI model engines require gigabytes of system memory and high-end processors to run locally. Reach for smolmaxxing when you want to run AI models on low-spec hardware by reading model data directly from device storage.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-13. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map