Empowering entrepreneurs through innovation and strategic growth with @haltium. Transforming ideas into successful businesses. #Innovation#Entrepreneurship
Ya salió el nuevo modelo de Google de su familia @googlegemma#Gemma4. Es un modelo de 12B que cae justo en medio entre los hermanos pequeños E2B y E4B y los grandes de 26B y 31B. Y gracias a @Prince_Canuma ya está disponible en MacOS
Today we’re introducing Gemma 4 12B — our latest open model that brings advanced agentic reasoning, vision and audio directly to your laptop.
It delivers performance nearing our larger Gemma models with a much smaller total memory footprint, while being small enough to run locally with just 16GB of VRAM. It’s open and accessible for everyone to use under a permissive Apache 2.0 license.
This is all made possible by our new, unified architecture that removes separate multimodal encoders. Here’s how we did it 🧵
@NousResearch@StepFun_ai How can I activate it? Is there some bug? Hermes was trying using a code for the OAuth, we tried several time and it didn’t work. We thought that maybe the model would know if it was Hermes so we ran it through OpenRouter and now Hermes died
@Prince_Canuma@haoailab@ltx_model Sure!! Don’t worry man! It was more like some sort of joke, I’m really impressed with what you do and you ability to turn to MLX anything I see. Best regards!!