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

FareedKhan-dev/kimi-k3-in-c

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

#LLM inference
Visit GitHub
C
10.1k
1.6k
1 contributors
Apache License 2.0
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 FareedKhan-dev/kimi-k3-in-c 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 5 – Nov 4, 2026

Stars +3,011 in 61 days

0200400600
434

Forks +471 in 61 days

0204060
58

Merged PRs 1 in 61 days

01
1

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

Top 25 in C

23231738151824522318
Sep 5Sep 13Sep 21Sep 29Oct 7Oct 15Oct 23Oct 31
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
Sat, Sep 5, 2026+18+50Not trending
Sun, Sep 6, 2026+23+70Not trending
Mon, Sep 7, 2026+25+70Not trending
Tue, Sep 8, 2026+30+80#23
Wed, Sep 9, 2026+127+120#2
Thu, Sep 10, 2026+186+171#3
Fri, Sep 11, 2026+56+120#17
Sat, Sep 12, 2026+194+260#3
Sun, Sep 13, 2026+77+190#8
Mon, Sep 14, 2026+69+130#15
Tue, Sep 15, 2026+36+30Not trending
Wed, Sep 16, 2026+35+40Not trending
Thu, Sep 17, 2026+25+50Not trending
Fri, Sep 18, 2026+25+70Not trending
Sat, Sep 19, 2026+41+40#18
Sun, Sep 20, 2026+30+80Not trending
Mon, Sep 21, 2026+19+40Not trending
Tue, Sep 22, 2026+180+200#2
Wed, Sep 23, 2026+128+170#4
Thu, Sep 24, 2026+109+270#5
Fri, Sep 25, 2026+102+210#2
Sat, Sep 26, 2026+25+50Not trending
Sun, Sep 27, 2026+42+90#23
Mon, Sep 28, 2026+50+110#18
Tue, Sep 29, 2026+27+60Not trending
Wed, Sep 30, 2026+20+60Not trending
Thu, Oct 1, 2026+14+50Not trending
Fri, Oct 2, 2026+8+80Not trending
Sat, Oct 3, 2026+26+10Not trending
Sun, Oct 4, 2026+15+20Not trending
Mon, Oct 5, 2026+5+70Not trending
Tue, Oct 6, 2026+26+90Not trending
Wed, Oct 7, 2026+18+50Not trending
Thu, Oct 8, 2026+14+40Not trending
Fri, Oct 9, 2026+19+30Not trending
Sat, Oct 10, 2026+9+20Not trending
Sun, Oct 11, 2026+20+60Not trending
Mon, Oct 12, 2026+20+20Not trending
Tue, Oct 13, 2026+20+30Not trending
Wed, Oct 14, 2026+17+10Not trending
Thu, Oct 15, 2026+8+20Not trending
Fri, Oct 16, 2026+18+30Not trending
Sat, Oct 17, 2026+15+10Not trending
Sun, Oct 18, 2026+7+30Not trending
Mon, Oct 19, 2026+14+00Not trending
Tue, Oct 20, 2026+20+30Not trending
Wed, Oct 21, 2026+12+50Not trending
Thu, Oct 22, 2026+15+30Not trending
Fri, Oct 23, 2026+11+10Not trending
Sat, Oct 24, 2026+9+50Not trending
Sun, Oct 25, 2026+8+20Not trending
Mon, Oct 26, 2026+6+10Not trending
Tue, Oct 27, 2026+10+20Not trending
Wed, Oct 28, 2026+19+20Not trending
Thu, Oct 29, 2026+13+30Not trending
Fri, Oct 30, 2026+17+00Not trending
Sat, Oct 31, 2026+13+30Not trending
Sun, Nov 1, 2026+11+50Not trending
Mon, Nov 2, 2026+154+170Not trending
Tue, Nov 3, 2026+434+580Not trending
Wed, Nov 4, 2026+267+110Not trending
Total+3,011+4711
  • 1#1 on the list
  • 7Rank that day
  • Not trending
1

    • GitHub trending history

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

    Nov 4, 2026Best #11

    #1#5#10#15#20#25
    Top 10
    Nov 4, 2026
    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 FareedKhan-dev/kimi-k3-in-c, and every badge it has earned
    1. Nov 42 posts

      • Testé kimi-k3-in-c sur un vieux laptop en local. Faire tourner un modèle de 2.78T paramètres sur un unique CPU avec 8.24 Go de RAM en C99 pur tient de l'exercice de style chirurgical. Le compromis se…

        Read full on X, posted by @clxymox

        @clxymox · x.com

      • 🛡️ Run massive AI locally without handing your data to third-party APIs. Execute a 2.78-trillion-parameter model in pure C99 using just 8.24 GB of RAM. #OpenSource #SelfHosted #C

        Read full on X, posted by @popmemecoin

        @popmemecoin · x.com

    2. Nov 32 posts

      • A 2.78-trillion-parameter model running on 8 GB of RAM, no GPU. kimi-k3-in-c does it by streaming the weights from disk, so you need ~1.56 TB of storage and about 26.5 s per token (the author's own…

        Read full on X, posted by @SadraMajidi04

        @SadraMajidi04 · x.com

      • Kimi-k3-in-C: A 2.78T-parameter model. No GPU. 8 GB of RAM

        Read full on Hacker News

        Hacker News

    3. Nov 21 post

      • 这个项目 可以吧Kimi k3 完整的2.8T参数跑在8G内存的设备上🥲 8G内存运行 Kimi k3，这词有点小众了🥲 但是速度大概是 0.03 tok/s 左右，差不多23s-30s 出一个Token🤡 能接受这速度的兄弟们可以试试🤓

        Read full on X, posted by @ai_funss

        @ai_funss · x.com

    4. 12 days earlier
    5. Oct 211 post

      • 2.78 万亿超大参数的模型，居然能在一台 8GB 内存的普通单核 CPU 上跑起来。 关注模型底层优化的工程师建议存下这个案例。 仓库地址：

        Read full on X, posted by @liangzhu_AI

        @liangzhu_AI · x.com

    6. 15 days earlier
    7. Oct 61 post

      • 这似乎可以移植到 PVM 上，不过没有意义... ,纯好玩

        Read full on X, posted by @libingjiang47

        @libingjiang47 · x.com

    8. Oct 51 post

      • 2.78 万亿参数的大模型，8GB 内存笔记本也能跑。 kimi-k3-in-c：整个引擎只有 176KB，纯 C99 无 GPU。1.56TB 模型放硬盘上按需流读，输出和 128GB 机器逐字节一致。内存只买速度：8GB 一个 token 26.5 秒，128GB 5.6 秒。 开源俩月 8.9k star。 #AI #开源 #硬核

        Read full on X, posted by @ataosky

        @ataosky · x.com

    9. 11 days earlier
    10. Sep 242 posts

      • Don't write your own inference engine. Not because it's hard. Because it will work. It'll build. It'll load. It'll decode fluent English. And it will be running a model that is not the one you…

        Read full on X, posted by @BuiltByNav

        @BuiltByNav · x.com

      • Don't read this if you just bought a GPU. Someone got a 2.78 trillion parameter model running on a laptop CPU. 8 GB of RAM. Zero GPUs. Now the catch, because it's a big one: 26 seconds per word.…

        Read full on X, posted by @TheUltronAi

        @TheUltronAi · x.com

    You might also like

    Repositories close to FareedKhan-dev/kimi-k3-in-c
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

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

    sqliteai/warp

    C

    Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.

    2.5k204

    robitec97/gemma3.c

    C

    Gemma 3 pure inference in C

    1178

    melonmath/microkimi

    Rust

    The Kimi K3 and DeepSeek-V4-Flash-0731 architectures, reimplemented from scratch in pure Rust (zero dependencies) and verified 1:1 against the official code.

    262

    adriancable/qwen3.c

    C

    Local Qwen3 LLM inference. One easy-to-understand file of C source with no dependencies.

    21725

    kishida/llama.cpp

    LLM inference in C/C++

    243

    google/gemma.cpp

    C++

    lightweight, standalone C++ inference engine for Google's Gemma models.

    7.1k684

    ifm-ai/llama.cpp

    LLM inference in C/C++

    2618

    shifulegend/project-zero

    C

    CPU-optimized LLM inference engine (C)

    553

    gavamedia/deltafin

    Rust

    Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.

    858119