DeepSeek-V4-Flash-Vision-Exp

amulyabaral 20 points 5 comments August 31, 2026
huggingface.co · View on Hacker News

Discussion Highlights (2 comments)

syntaxing

I’m honestly surprised this is better benchmark wise than the text only model. I figured the addition of vision would take away from some of the text capabilities.

BrucecarlL

I'm not that impressed with this version. When using it, it often acts as if it has no visual capability and refuses to recognize images unless I remind it.

Semantic search powered by Rivestack pgvector
5,118 stories · 46,096 chunks indexed