RepoAlerts

hyperionaidev/smolmaxxing

Can I trust it?

Worth a closer look before you use it.

  • Warnings Check

    Very new: it was created 12 days ago. Wait a little before installing it.

  • Stars from real accounts No data

    We haven't checked its stars for fakes yet.

  • Active OK

    Last change 2 days ago.

  • Licence OK

    MIT: you can use it for free, also in a commercial product. Keep the licence notice.

Quick checks from public data. They help, but they are no guarantee.

What it is

A research project that runs large language models on low-power devices such as TV boxes and old tablets. It patches llama.cpp with custom kernels, reduced memory use and expert weights streamed from flash, and reports measured speeds per device.

Who it's for

Developers and hobbyists who want to run LLMs on old or low-RAM ARM hardware, such as Android TV boxes or jailbroken iPads

How to use it

Ask your AI to set it up

Paste this into Claude, ChatGPT or your coding assistant.

Help me install and set up hyperionaidev/smolmaxxing in my project. Follow its README: https://github.com/hyperionaidev/smolmaxxing. Explain each step and check it is safe before running anything.

Read the README

Star curve

778From 0 to 778 stars between 4 Nov 2026 and 16 Nov 2026.

On the radar

13 Nov 2026: #1014 Nov 2026: #1915 Nov 2026: #9116 Nov 2026: #72
Best place #10, on 13 Nov 2026. In the top 100 on 4 of the last 30 days.

Its place among the radar's top 100, day by day, with #1 at the top. Gaps are days it was out of the top 100.

Records

  • Best place on RepoAlerts: #10, on 13 Nov 2026
  • In the top 10 for 1 day, on 13 Nov 2026
  • In the top 100 for 3 days since 13 Nov 2026
  • On the Hacker News front page on 12 Nov 2026

Alternatives

Similar projects named in its profile. Each link searches the directory.

On Hacker News

Get alerts for repos like this

We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.

What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy

For maintainers

Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.

[![hyperionaidev/smolmaxxing on RepoAlerts](https://repoalerts.com/badge/hyperionaidev/smolmaxxing.svg)](https://repoalerts.com/repo/hyperionaidev/smolmaxxing?ref=badge)
Share on X

  • JakeATX/llamAmpere

    A fork of llama.cpp tuned for NVIDIA RTX 30-series Ampere GPUs, especially the RTX 3090 and 3090 Ti. It runs Qwen3.8 models, including Qwen3.8-27B with its built-in MTP draft head and a Flash-Next var

    AppModels & inferenceC++ · 383 stars · +83 this week · 70 days old

  • manuelgscom/inside-llm

    A native binary that loads one or two GGUF models via llama.cpp and shows in the browser per-token probabilities, discarded alternatives, sampler effects, and the token where two models' outputs diver

    AppModels & inferenceTypeScript · 70 stars · +70 this week · 1 day old

  • abhi245y/PS5LM-Plus

    A native app that runs llama.cpp on a jailbroken PlayStation 5 using its GPU via Vulkan. It loads GGUF models from internal or USB storage, shows a dashboard on the TV, and exposes a chat UI and OpenA

    Models & inferenceC++ · 521 stars · +10 this week · 38 days old

  • samir-sarwar/samir-vllm

    A learning-oriented LLM inference engine written in C++17 and CUDA that runs Llama 3.2 1B Instruct. It loads safetensors weights to the GPU, implements tokenizer, prefill and decode with paged KV cach

    ResourceModels & inferenceC++ · 223 stars · +123 this week · 82 days old · HN 80 pts

  • Betelgeuse-AI/Betelgeuse

    A llama.cpp fork that runs mixture-of-experts models larger than GPU memory on an RTX 3060 12 GB. Dense weights stay on the GPU, while routed experts are paged from local NVMe into a bounded VRAM slot

    AppModels & inferenceC++ · 154 stars · +31 this week · 16 days old

  • HalfVulpes/Deepinfer-SM80

    Ports DeepSeek's DeepInfer kernels and engine optimizations from Blackwell to NVIDIA Ampere SM80/SM86 GPUs for vLLM V1. Ships two vLLM patches plus drop-in Python, Triton and TileLang modules targetin

    LibraryModels & inferencePython · 200 stars · 27 days old