DeepSeek's V4.1-Flash Beats Its Own Flagship at a Quarter of the Memory Cost
This story is from 2026-09-10. It is preserved in the archive; the latest stories are on the live feed.
DeepSeek's 552B mixture-of-experts model splits input and output compute asymmetrically, natively handles vision, and undercuts its own flagship on price.
Read the full story at AlphaSignal ↗
Timeline · 1 report
- 2026-09-10 06:10 · AlphaSignal
DeepSeek's V4.1-Flash Beats Its Own Flagship at a Quarter of the Memory Cost