view article Article Kimi K3 Model Overview: 2.8T Parameters, MXFP4 Quantization, and What the Open Weights Mean for the Community ResterChed • 23 days ago • 195
view article Article DeepSeek-V4: a million-token context that agents can actually use burtenshaw • Apr 24 • 53
view article Article LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family lightonai • Jan 19 • 102
view article Article Continuous batching from first principles +1 ror, ArthurZ, mcpotato • Nov 25, 2025 • 432