Log inSign up
Georgi Gerganov
1,771 posts
Georgi Gerganov profile banner
@ggerganov

Georgi Gerganov

@ggerganov
24th at the Electrica puzzle challenge | building github.com/ggml-org | engineer @huggingface
github.com/ggerganov
Joined May 2015
294
Following
71.4K
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @ggerganov
    Georgi Gerganov
    @ggerganov
    Sep 4
    Hugging Face has been acquired by NVIDIA It is quite exciting to be a part of this journey! NVIDIA has been an active supporter of the llama.cpp project. For more than a year now, their engineers have actively contributed to the codebase, collaborated with the community and
    28
  • @ggerganov
    Georgi Gerganov
    @ggerganov
    Sep 1
    The Llama app for Mac now comes with a simple request builder for llama.cpp's REST API
    Image
    00:00
    14
  • @ggerganov
    Georgi Gerganov
    @ggerganov
    Aug 17
    let that sink in
    Image
    120
  • @ggerganov
    Georgi Gerganov
    @ggerganov
    Aug 17
    I find the "inception" pattern to be very useful in many agentic use cases. You can force the model to take an action when it thinks for too long by injecting a thought after a specified reasoning budget. Helps dealing with underspecified tasks which make the model reason for
    @ggerganov
    Georgi Gerganov
    @ggerganov
    Aug 17
    Replying to @ggerganov
    to limit the max reasoning length, add: ... \ --reasoning-budget 4096 \ --reasoning-budget-message "... I am thinking for too -- let me gather more info about the task." adjust to your needs
    27
  • @ggerganov
    Georgi Gerganov
    @ggerganov
    Aug 14
    simple: llama serve -hf ggml-org/Qwen3.8-27B-GGUF --spec-type draft-mtp
    34
Advertisement
Advertisement