Developer Distills DeepSeek V4 Flash into 4B Model on DGX Spark in 26 Hours

A Japanese developer used DGX Spark to distill the 157GB DeepSeek V4 Flash into a 4B model in about 26 hours, achieving per-judgment inference of only 22ms.

2026-09-19 ~ 2026-09-20 · 2 related posts

• Distilling DeepSeek V4 Flash to a 4B model on DGX Spark: 26 hours, 22ms per judgment — Dan_Jeffries1 · 2026-09-19

1 near-duplicate retellings: alexcovo_eth