Log inSign up
Georgi Gerganov
1,740 posts
user avatar
Georgi Gerganov
@ggerganov
24th at the Electrica puzzle challenge | building github.com/ggml-org | engineer @huggingface
github.com/ggerganov
Joined May 2015
292
Following
62.3K
Followers

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

TermsยทPrivacyยทCookiesยทAccessibilityยทAds Infoยทยฉ 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • Pinned
    user avatar
    Georgi Gerganov
    @ggerganov
    Mar 30
    llama.cpp at 100k stars now that 90% of the code worldwide is being written by AI agents, I predict that within 3-6 months, 90% of all AI agents will be running locally with llama.cpp ๐Ÿ˜„ Jokes aside, I am going to use this small milestone as an opportunity to reflect a bit on
    460K
  • user avatar
    Georgi Gerganov
    @ggerganov
    Feb 24, 2025
    Today I was sent the following cool demo: Two AI agents on a phone call realize theyโ€™re both AI and switch to a superior audio signal ggwave
    00:00
    18M
  • user avatar
    Georgi Gerganov
    @ggerganov
    Mar 26, 2023
    Introducing LLaMA voice chat! ๐Ÿฆ™ You can run this locally on an M1 Pro
    00:00
    1.7M
  • user avatar
    Georgi Gerganov
    @ggerganov
    Jan 27, 2025
    pack it up boys, it's over
    706K
  • user avatar
    Georgi Gerganov
    @ggerganov
    Feb 24, 2025
    Replying to @ggerganov
    The developers (Anton and Boris) used the ggwave library to make the AIs communicate faster over a phone call
    GitHub - ggerganov/ggwave: Tiny data-over-sound library
    From github.com
    1.1M
  • user avatar
    Georgi Gerganov
    @ggerganov
    Sep 7, 2023
    Casually running a 180B parameter LLM on M2 Ultra
    00:00
    683K
  • user avatar
    Georgi Gerganov
    @ggerganov
    Jun 6, 2023
    I've started a company: ggml.ai From a fun side project just a few months ago, ggml has now become a useful library and framework for machine learning with a great open-source community
    1.1M
  • user avatar
    Georgi Gerganov
    @ggerganov
    Mar 27, 2023
    LLaMA voice chat + Siri TTS This example is now truly 100% offline since we are now using the built-in Siri text-to-speech available on MacOS through the "say" command
    00:00
    412K
  • user avatar
    Georgi Gerganov
    @ggerganov
    Feb 24, 2025
    Replying to @ggerganov
    The "gibberlink" project is hosted here: github.com/PennyroyalTea/โ€ฆ They won 1st place in a hackaton competition! Congrats!
    GitHub - PennyroyalTea/gibberlink: Two conversational AI agents switching from English to sound-l...
    From github.com
    608K
  • user avatar
    Georgi Gerganov
    @ggerganov
    Mar 3, 2025
    Here is another Gibberlink experiment: Two AI agents autonomously encrypt their audio chat (video by Anton Pidkuiko)
    00:00
    271K
  • user avatar
    Georgi Gerganov
    @ggerganov
    May 28, 2024
    llama.cpp is now in Homebrew Core ๐Ÿบ
    198K
  • user avatar
    Georgi Gerganov
    @ggerganov
    Aug 31, 2023
    Full F16 precision 34B Code Llama at >20 t/s on M2 Ultra
    00:00
    1.2M
  • user avatar
    Georgi Gerganov
    @ggerganov
    Jul 12, 2023
    ggtag : data-over-sound is back ! Please checkout our latest geeky side project -- An e-paper badge that can be programmed with sound Here is how it works ๐Ÿ”Š
    00:00
    203K
  • user avatar
    Georgi Gerganov
    @ggerganov
    Sep 5, 2023
    sam.cpp ๐Ÿ‘€ Inference of Meta's Segment Anything Model on the CPU Project by @YavorGI - powered by ggml.ai
    00:00
    265K