The setup was modest. Two RTX 4090s in my basement ML rig, running quantised models through ExLlamaV2 to squeeze 72-billion parameter models into consumer VRAM. The beauty of this method is that you don’t need to train anything. You just need to run inference. And inference on quantized models is something consumer GPUs handle surprisingly well. If a model fits in VRAM, I found my 4090’s were often ballpark-equivalent to H100s.
顾诗韬是另一位联合创始人，长期负责复杂系统的软硬件集成。她更多出现在台前，负责公司整体战略、产品定义与对外沟通，包括融资、上市节奏以及与央视春晚等平台的合作。
，详情可参考wps
Global news & analysis，更多细节参见手游
Head coach hails captain Harry Brook’s ‘amazing job’。关于这个话题，whatsapp提供了深入分析
Gotit.pub (What is GotitPub?)