News for hackers. Stuff that matters.
Re:DeepSeek v4 by littlestymaar on Friday April 24, 2026 @09:06AM (#47889677)
How can a medium-sized model like Deepseek-V4-Flash be cheaper than a much smaller models like Qwen3.5-35B-A3B.

It's five times bigger in both total and active parameters!

Re:DeepSeek v4 by Ancapistani on Friday April 24, 2026 @12:54PM (#47892815)
I don’t know for sure, but I believe those larger models must be run on nVidia hardware (CUDA), while Deepseek-V4-* can be run on Huawei chips. My assumption is that there is less demand pressure on non-nVidia chips.