DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Paper • 2609.19969 • Published 10 days ago • 182
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search Paper • 2609.13356 • Published 16 days ago • 263
128GB UMA Models Collection Models optimized for Strix Halo and similar systems • 7 items • Updated 27 days ago • 7