Sabitlenmiş Tweet

Running this model to power Hermes Agent on a MacBook Pro M3 Max with 36GB of memory. Insane performance! Talking to my OpenClaw and Hermes bots together in Discord in a group chat is mind blowing.
Julien Chaumond@julien_c
Just do this: brew install llama.cpp --HEAD Then; llama-server -hf ggml-org/gemma-4-26B-A4B-it-GGUF:Q4_K_M
English










































