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

Bifrost
Bifrost

RightNow-AI/picolm

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

#LLM inference
Visit GitHub
C
2.2k
302
4 contributors
MIT License
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

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

Momentum

How fast RightNow-AI/picolm 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

Sep 9 – Nov 5, 2026

Stars +295 in 58 days

050100150
140

Forks +59 in 58 days

051015
13

Merged PRs 0 in 58 days

01

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

Top 25 in C

6211
Sep 9Sep 17Sep 25Oct 3Oct 11Oct 19Oct 27Nov 4
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 PRsC
Wed, Sep 9, 2026+2+00Not trending
Thu, Sep 10, 2026+2+00Not trending
Fri, Sep 11, 2026+0+00Not trending
Sat, Sep 12, 2026+0+00Not trending
Sun, Sep 13, 2026+40+50#6
Mon, Sep 14, 2026+140+110#2
Tue, Sep 15, 2026+44+130#11
Wed, Sep 16, 2026+21+20Not trending
Thu, Sep 17, 2026+11+20Not trending
Fri, Sep 18, 2026+2+00Not trending
Sat, Sep 19, 2026+1+00Not trending
Sun, Sep 20, 2026+1+00Not trending
Mon, Sep 21, 2026+3+00Not trending
Tue, Sep 22, 2026+3+00Not trending
Wed, Sep 23, 2026+0+00Not trending
Thu, Sep 24, 2026+0+00Not trending
Fri, Sep 25, 2026+4+00Not trending
Sat, Sep 26, 2026+0+00Not trending
Sun, Sep 27, 2026+0+00Not trending
Mon, Sep 28, 2026+0+00Not trending
Tue, Sep 29, 2026+0+00Not trending
Wed, Sep 30, 2026+1+10Not trending
Thu, Oct 1, 2026+1+10Not trending
Fri, Oct 2, 2026+0+00Not trending
Sat, Oct 3, 2026+2+00Not trending
Sun, Oct 4, 2026+0+00Not trending
Mon, Oct 5, 2026+1+00Not trending
Tue, Oct 6, 2026+0+00Not trending
Wed, Oct 7, 2026+0+00Not trending
Thu, Oct 8, 2026+0+00Not trending
Fri, Oct 9, 2026+3+00Not trending
Sat, Oct 10, 2026+0+00Not trending
Sun, Oct 11, 2026+2+00Not trending
Mon, Oct 12, 2026+2+00Not trending
Tue, Oct 13, 2026+0+00Not trending
Wed, Oct 14, 2026+0+20Not trending
Thu, Oct 15, 2026+0+10Not trending
Fri, Oct 16, 2026+0+60Not trending
Sat, Oct 17, 2026+1+40Not trending
Sun, Oct 18, 2026+1+70Not trending
Mon, Oct 19, 2026+1+30Not trending
Tue, Oct 20, 2026+0+00Not trending
Wed, Oct 21, 2026+1+00Not trending
Thu, Oct 22, 2026+1+00Not trending
Fri, Oct 23, 2026+0+00Not trending
Sat, Oct 24, 2026+0+00Not trending
Sun, Oct 25, 2026+0+10Not trending
Mon, Oct 26, 2026+1+00Not trending
Tue, Oct 27, 2026+0+00Not trending
Wed, Oct 28, 2026+0+00Not trending
Thu, Oct 29, 2026+1+00Not trending
Fri, Oct 30, 2026+1+00Not trending
Sat, Oct 31, 2026+0+00Not trending
Sun, Nov 1, 2026+1+00Not trending
Mon, Nov 2, 2026+0+00Not trending
Tue, Nov 3, 2026+0+00Not trending
Wed, Nov 4, 2026+0+00Not trending
Thu, Nov 5, 2026+0+00Not trending
Total+295+590
  • 1#1 on the list
  • 7Rank that day
  • Not trending
3
  • GitHub trending history

    Where the repository ranked on GitHub Trending, one dot for each day it was on a list

    C

    Apr 27 – Sep 16, 2026Best #3

    #1#5#10#15#20#25
    Top 10
    May 2026JunJulAugSep
    The left and right arrow keys step from day to day; Home and End go to the first and the last

    Mentions and achievements

    Where people are talking about RightNow-AI/picolm, and every badge it has earned
    1. Aug 32 posts
      • 一个用约 2500 行纯 C(C11)编写的极简 LLM 推理引擎,能够在仅 256MB RAM、售价 10 美元的嵌入式单板电脑上本地运行 TinyLlama 等十亿参数级别的大模型,实现真正离线、零依赖、极低成本的 AI 推理。

        Read full on X, posted by @weiwei2018831

        @weiwei2018831 · x.com

      • • Pure C11, zero dependencies, single ~80KB binary • Memory-maps a 638MB model, using only 45MB runtime RAM • Runs on Raspberry Pi Zero 2W, LicheeRV RISC-V, and x86-64

        Read full on X, posted by @the_osps

        @the_osps · x.com

    2. Aug 21 post
      • 在 256MB 内存的廉价开发板上本地运行十亿参数级 LLM 的纯 C 推理引擎 PicoLM 是约 2500 行 C11 写的极简 LLM 推理引擎,零依赖、单文件约 80KB,能在树莓派 Zero 2W、LicheeRV Nano 这类廉价板子上跑 TinyLlama 1.1B 等 GGUF 模型。

        Read full on X, posted by @QingQ77

        @QingQ77 · x.com

    3. Jul 311 post
      • 用 10 美元的开发板,256MB 内存,跑十亿参数的大模型,这事真有人做出来了。 PicoLM 是纯 C 写的推理程序,编译出来单个文件约 80KB 大小,零依赖,运行占 45MB 内存。 在树莓派 5 上每秒大约 10 个 Token,树莓派 4 是 8 个,十美元那块板子也有 1 个。 GitHub: 作者拿它给 PicoClaw 当本地大脑,两个凑一起就是个全程离线的…

        Read full on X, posted by @GitHub_Daily

        @GitHub_Daily · x.com

    4. 27 days earlier
    5. Jul 41 post
      • Run a 1B model on a $10 board — without Python or the cloud. PicoLM is a minimal, from-scratch LLM inference engine written in C11 for running TinyLlama 1.1B and other LLaMA-architecture GGUF models…

        Read full on X, posted by @DanKornas

        @DanKornas · x.com

    6. 1 month earlier
    7. May 261 post
      • Runs 1B parameter LLM on $10 board

        Read full on X, posted by @tom_doerr

        @tom_doerr · x.com

    You might also like

    Repositories close to RightNow-AI/picolm
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

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

    Tiiny-AI/PowerInfer

    C++

    High-speed Large Language Model Serving for Local Deployment

    9.9k659

    jitllm/jitllm

    Go

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

    585

    Picovoice/picollm

    Python

    On-device LLM Inference Powered by X-Bit Quantization

    31827

    emrehangorgec/awesome-llm-on-anything

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

    24

    lvyufeng/PocketLLM

    Python

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

    5510

    aweussom/NoLlama

    Python

    NPU Ollama - An Ollama/OpenAI compatible API for Intel OpenVINO compatible computers

    13221

    pytorch/torchchat

    Python

    Run PyTorch LLMs locally on servers, desktop and mobile

    3.6k247

    memovai/mimimodel

    C

    MimiModel: Agentic LLM on a $5 chip. 100% on-device. Private by design.

    9911

    mitsuhiko/pi-llamacpp

    TypeScript

    An experimental pi extension that runs and manages qwen with llama.cpp

    14513