About this app
Shadow-test local Ollama models against a cloud baseline with a multi-judge ensemble. Automatically promotes models when statistically proven equivalent — re...
🔌
需要 ClawBox 硬件
在您自己的 AI 硬件上本地运行 Llm Eval Router — 私密、快速、无需云端。
Shadow-test local Ollama models against a cloud baseline with a multi-judge ensemble. Automatically promotes models when statistically proven equivalent — re...
需要 ClawBox 硬件
在您自己的 AI 硬件上本地运行 Llm Eval Router — 私密、快速、无需云端。
