Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Omnigraph
Omnigraph
Websitebench
Websitebench
Bifrost
Bifrost
Busbar
Busbar

hyperionaidev/smolmaxxing

maxxing the ability to run different LLMs on the smallest devices possible

#LLM inference
Visit GitHub
C
494
2 contributors
MIT License
FeaturedAdvertise to 180K+ monthly visitors
Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Websitebench

Can AI agents reverse-engineer real websites?

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Busbar

Control what AI can do before it acts

Momentum

How fast hyperionaidev/smolmaxxing is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Nov 11 – Nov 13, 2026

Stars +468 in 3 days

0100200300
236

Forks +0 in 3 days

01

Merged PRs 0 in 3 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Nov 11Nov 12Nov 13
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Wed, Nov 11, 2026+0+00
Thu, Nov 12, 2026+232+00
Fri, Nov 13, 2026+236+00
Total+468+00
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Social mentions

Recent discussions about this repository across the web
  1. Nov 135 posts
    • 11 月 13 日,开源的 smolmaxxing 作者自测:小米电视盒子 S 第三代(约 1GB 可用内存)跑 Qwen3.5-2B 7.7 tok/s、16B Ling-mini-2.0 5.1 tok/s;2013 款越狱 iPad Air 跑 1-bit Bonsai-1.7B 24-26 tok/s、Ling-mini-2.0 2.6-4.5…

      Read full on X, posted by @Moblacksoil

      @Moblacksoil · x.com

    • 家里闲着的旧设备,比如一台越狱过的 iPad,也能跑 8B、16B 的 MoE 模型了。有人专门在做这件事,项目叫 smolmaxxing。 思路很直接:电视盒子、旧平板、单板机、路由器都有 CPU,有一点内存和闪存,一天里大部分时间闲着。作者先摸清每台设备实际跑得动的最大模型,再靠定制内核、省着用内存、从闪存流式读权重,把这个上限往上推。 最狠的一条:作者说,测过的两台设备都能在大约 1 GB…

      Read full on X, posted by @xqliu

      @xqliu · x.com

    • AI Updates - 13 Nov 2026 🤖 Google released Gemini 4 Hydrogen, its fast, cheap model for agents and everyday work. It costs $1.50 per million input tokens and scores 51 on the Artificial Analysis…

      Read full on X, posted by @madhugogineni97

      @madhugogineni97 · x.com

    • 3. alexeyw/lot-map A Claude Code plugin that draws a live map beside the chat. Every tool call, skill and model step pulses to its station (files, shell, web, agents), so you see the work instead of…

      Read full on X, posted by @Yashpatil

      @Yashpatil · x.com

    • 13年前的 iPad Air,还能跑本地 AI 聊天。 作者在1GB内存的老平板上,改程序跑了个小模型。每秒生成约25个文本片段(token),长聊18~22个。 项目叫 smolmaxxing,源码和失败实验都公开了。手里有旧平板的可以看看,复现要越狱,还得用作者修改的程序。

      Read full on X, posted by @MarcosPurs46815

      @MarcosPurs46815 · x.com

  2. Nov 122 posts
    • PostgreSQL 18.7, 17.12, 16.16, 15.20, 14.25, and 19 RC 2 Released (

      Read full on X, posted by @betterhn50

      @betterhn50 · x.com

    • I'm making LLMs work on small and old devices

      Read full on Hacker News

      Hacker News

You might also like

Repositories close to hyperionaidev/smolmaxxing
FeaturedAdvertise to 180K+ monthly visitors
Omnigraph

Versioned graph database on object storage. Git-style workflows and multimodal retrieval

Websitebench

Can AI agents reverse-engineer real websites?

Busbar

Control what AI can do before it acts

Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

jitllm/jitllm

Go

Smart inference engine that adapts to your hardware to run models faster, even when they don’t fit in memory

586

0xSojalSec/airllm

Jupyter Notebook

Runs 405B LLMs on 8GB VRAM

3.1k249

Tiiny-AI/PowerInfer

C++

High-speed Large Language Model Serving for Local Deployment

9.9k664

lyogavin/airllm

Jupyter Notebook

AirLLM 2.8T LLM inference with single 4GB GPU

42.3k4.3k

emrehangorgec/awesome-llm-on-anything

Language models running locally on hardware that has no business running them

25

RightNow-AI/picolm

C

Run a 1-billion parameter LLM on a $10 board with 256MB RAM

2.2k302

lvyufeng/PocketLLM

Python

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware

5510

mlc-ai/mlc-llm

Python

Universal LLM Deployment Engine with ML Compilation

23.4k2.3k

Tylogi/TyloQuant

C++

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the hardware you already own.

9515