Georgi Gerganov

@ggerganov

24th at the Electrica puzzle challenge | building github.com/ggml-org | engineer @huggingface

Pinned
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 😄 Jokes aside, I am going to use this small milestone as an opportunity to reflect a bit on
Georgi Gerganov
@ggerganov
Aug 17
let that sink in
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
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
Georgi Gerganov
@ggerganov
Aug 14
simple: llama serve -hf ggml-org/Qwen3.8-27B-GGUF --spec-type draft-mtp
Georgi Gerganov
@ggerganov
Jul 16
Run upgraded Gemma 4 with llama.cpp (QAT + MTP)
Google Gemma
@googlegemma
Jul 15
We’re rolling out some big improvements to Gemma 4, fueled by incredible community feedback and contributions! Here is a breakdown of what’s being fixed and updated in this release: 🧵👇