Long-form technical write-ups behind this site's numbers — formulas, worked examples and sources. The same math powers the calculator.
KDA, Gated DeltaNet, Mamba and sliding-window attention break the classic KV-cache formula. The exact per-layer state math, worked examples for Kimi K3 / Qwen3-Next / Gemma 3 / gpt-oss, and how vLLM, llama.cpp and SGLang actually bill the memory.
2026-08-28
Parameter heuristics and benchmark tables both fail in instructive ways. The Speed-of-Light model behind this site: prefill vs decode rooflines, the corrections that matter (frameworks, quantization, MoE, hybrid attention, TP sublinearity), and the three-way calibration that keeps it honest — including where it is wrong.
2026-08-28