+ new component
new QAT quants are available now if you want to run Gemma 4 12B in only 6.7 GiB VRAM
blog.google/innovation-a...
Just watched Weapons.
Pretty fun!
I liked the narrative style.
It's another movie that can be easily spoiled, be careful. Go watch it!
What would happen if we tried the diffusion generation on LLMs?
We get Diffusion Gemma!
4x speed up! ⚡⚡⚡💎
blog.google/innovation-a...
We’re releasing Gemma 4 quantization-aware training checkpoints, reducing memory requirements and improving on-device performance.
blog.google