The one I showed at yesterday's study session
The one I showed at yesterday's study session: Using two DGX Spark (PGX) machines, I submitted 16 requests to DeepSeek-V4-Flash-Vision-Exp + DSpark at the same time. I used MiaAI_lab's recipe. The result is 62.6 tok/s for a single request, and a total of 248.8 tok/s for 16 requests (about 4 times more)!
[Lutheran News Agency | Dr. Yan said | Editing] Xi Jinping's "SCO Summit" series: empty words and nonsense, and small calculations making noise.
9/1/2026 DrLiMengYAN1 ◉ Xi Jinping now urgently needs a "safe environment" and is afraid of "external forces interfering in internal affairs"
Estimated total ARR of Chinese OSS/Openweight AI is $10-15B = approximately 1.6-2.4 trillion yen📈
Listing the numbers of the major players👇 ・DeepSeek: Sales from January to July 2026 approximately 11.3 billion yen ・MiniMax: ARR over $800M = approximately 128 billion yen ・Moonshot / Kimi: ARR $200M = approximately 32 billion yen ・Zhipu /
How do big AIs cheat? So it can be stuffed into a home machine?
Series: The era when AI moves from the cloud to your desk, part 3 Last time we talked about tables and books. The table is the RAM, the book is the AI model, and the AI must have the entire book spread out on the table for it to work. Now comes the real problem. Really great book…
You have reached the end of the archive
All of deepseek