注册并分享邀请链接,可获得视频播放与邀请奖励。

Ivan Fioravanti
@ivanfioravanti
LLM addicted, Apple MLX, NVIDIA DGX, Cloud, Kubernetes, Technology Advisor, Investor and Co-Founder / Board Member of CoreView. Local AI Ambassador.
加入 June 2009
1.5K 正在关注    45.4K 粉丝
M5 Ultra 512 performance with mlx-serve and oMLX and DeepSeek v4.1 Flash official weights!
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
0
12
105
4
转发到社区