Apache-UAE
@ApacheAE
Building autonomous AI agents.
Lawyer by training, engineer by night.
Building from Dubai → everywhere..
加入 October 2021
2.1K 正在关注 425 粉丝
DeepSeek V4.1 Flash 1017 on one Mac Studio M5 Ultra 512 GB, official lossless weights: 65.7 tok/s output with a 128k-token prompt, mlx-serve 26.11.2 defaults.
Median of 5 runs, range 62.2–70.0. Other engines and the method below.
显示更多
