Loading activity…
@nielsrogge
ML Engineer @huggingface. Building http://paperswithco.de. @KU_Leuven grad. General interest in machine & deep learning. Making AI more accessible for everyone!
AI
OpenBMB released MiniCPM-V 4.7, saying its 35B-A3B variant reaches 13-plus tokens/sec on iPhone 17 Pro Max using 3GB memory.
AI
A post says she handles Hugging Face's Chinese ecosystem and praises her work there.
AI
The announcement shares Claude Code’s attempt to infer Jev’s architecture after being asked to research it with the search_papers tool.
AI
The user claims V4.1 is cheaper to serve than V4-Flash but costs twice as much per output token even off-peak.