The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction Paper β’ 2609.18063 β’ Published 3 days ago β’ 10
deepseek-ai/DeepSeek-V4.1-Flash Image-Text-to-Text β’ 763B β’ Updated 9 days ago β’ 430k β’ β’ 3.21k
orcarouter/GLM-5.3-Flash-Uncensored-GGUF Image-Text-to-Text β’ 321B β’ Updated 18 days ago β’ 29.1k β’ 68
AVO: Agentic Variation Operators for Autonomous Evolutionary Search Paper β’ 2603.24517 β’ Published Mar 25 β’ 13