# How DeepSeek Uses Less Memory

**Published:** October 18, 2026
**Author:** Matthew Berman
**Source:** YouTube — Matthew Berman
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/how-deepseek-uses-less-memory

the supply is constrained and thus the prices rise. So going back to DeepSeek, the KV cache only needs a fourth of the HBM and then they also need 1/8 of the SSD storage. Well, they're able to serve many more tokens without necessarily having to pay for all that memory. The…

> From the original source: **YouTube — Matthew Berman**
> [Read full article at YouTube — Matthew Berman](https://www.youtube.com/shorts/RS9vWYlJeH8)

**Tags:** #DeepSeek #YouTube

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*