
Shuo Yang
@Andy_ShuoYang • 4,711 subscribers
2nd year phd at Berkeley; Efficient ML System;
Videos

Your gaming PC can now serve frontier models at interactive speed using official checkpoints without extreme quantization! Qwen3.6 35B → 8GB RTX 4060 laptop @ 39 tok/s DeepSeek-V4-Flash 284B → RTX 5090 desktop @ 22-25 tok/s GLM-5.2 753B → RTX PRO 6000 workstation @ 15 tok/s Run your claude code or codex now with frontier model for $0 Meet FreeToken 🧵
Shuo Yang1,055,859 просмотров • 4 дней назад
Больше нет контента для загрузки