Back to AIBriefs
LaunchAI Models

Gemma 4 achieves 255 tok/s on WebGPU via Fable

Hugging Face
@huggingface

The AI community building the future. https://t.co/TpiXQMQ9rZ

NYC and Paris and 🌏huggingface.co
View on X
View on X
Hugging Face avatar
Hugging Face
@huggingface

RT @xenovacom: Before Fable 5 was shut down, it pushed Gemma 4 to 255 tok/s on WebGPU. Some didn't believe it was real. Today we're releas…

Gemma 4 E2B running in-browser at 255 tok/s using WebGPU kernels written by Fable 516 hours agoxenovatechDiscuss
·
14 hours ago
Gemma 4 achieves 255 tok/s on WebGPU via Fable — AIBriefs