https://hongping-zh.github.io/ 2026-06-22 weekly 1.0 https://hongping-zh.github.io/og-image.png LLM Energy Benchmark — Quantization Energy-Accuracy Trade-offs Real GPU power measurements for INT8, NF4, and FP16 LLM inference across 4 NVIDIA architectures, with perplexity accuracy data. https://hongping-zh.github.io/paper/ 2026-06-22 monthly 0.9 https://hongping-zh.github.io/og-image.png Weight-Only Quantization Does Not Always Save Energy https://hongping-zh.github.io/papers/ssrn-6854700.pdf 2026-06-22 monthly 0.8 https://hongping-zh.github.io/compare.html 2026-06-22 monthly 0.8 https://hongping-zh.github.io/updates/ 2026-06-08 weekly 0.6 https://hongping-zh.github.io/updates/2026-06-08-rtx-pro6000-fp16-e2e/ 2026-06-08 monthly 0.7 https://hongping-zh.github.io/updates/2026-06-03-rtx-pro6000-blackwell-phase/ 2026-06-03 monthly 0.7 https://hongping-zh.github.io/updates/2026-04-18-qwen25-3b-t4/ 2026-04-18 monthly 0.6 https://hongping-zh.github.io/bot-landing/ 2026-06-22 monthly 0.3