Merchant_Lawrence

Google releases Gemma 4 QAT. ✨
You can now run Gemma 4 at 3x less memory with near original performance.

QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.

GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qat
QAT Guide: https://unsloth.ai/docs/models/gemma-4/qat

1 reply

New activity in Steward/lcm-dreamshaper-v7-gguf 3 months ago

thanks for awesome lightweight model can share method to do it ?

#1 opened 3 months ago by

Ryu-Sena

upvoted a changelog 4 months ago

Hugging Face Changelog

Introducing Kernels

Apr 15

• 206

New activity in joyfox/Qwen-Image-Edit-2509-Upscale2K 9 months ago

Not sure if i use it wrong ? (wavespeed output look same)

#1 opened 9 months ago by

Ryu-Sena

upvoted an article 10 months ago

Article

We’re open-sourcing our text-to-image model and the process behind it

Photoroom

•

Nov 12, 2025

• 102

updated a dataset 10 months ago

Ryu-Sena/manga-text-removal-comparison

Viewer • Updated Nov 12, 2025 • 1 • 15

published a dataset 10 months ago

Ryu-Sena/manga-text-removal-comparison

Viewer • Updated Nov 12, 2025 • 1 • 15

reacted to jasoncorkill's post with 🔥 10 months ago

Post

4749

Do you remember https://thispersondoesnotexist.com/ ? It was one of the first cases where the future of generative media really hit us. Humans are incredibly good at recognizing and analyzing faces, so they are a very good litmus test for any generative image model.

But none of the current benchmarks measure the ability of models to generate humans independently. So we built our own. We measure the models ability to generate a diverse set of human faces and using over 20'000 human annotations we ranked all of the major models on their ability to generate faces. Find the full ranking here:
https://app.rapidata.ai/mri/benchmarks/68af24ae74482280b62f7596

We have release the full underlying data publicly here on huggingface: Rapidata/Face_Generation_Benchmark