L
LLM Inference Performance Estimator
0
⬇️ 下载量
100,000
⭐ 收藏
0
📦 安装量
Estimate LLM inference performance metrics including TTFT, decode speed, and VRAM requirements based on model architecture, GPU specs, and quantization format.
🔧 安装方式
复制提示词，发送给任意 AI 助手即可安装 Skill，包括但不限于 Lighthouse OpenClaw、WorkBuddy、QClaw、Kimi、Claude 等
请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub.cn/install/skillhub.md 安装 Skillhub 商店，然后安装 LLM Inference Performance Estimator 技能。
若已安装，则直接安装 LLM Inference Performance Estimator 技能。
Estimate LLM inference performance metrics including TTFT, decode speed, and VRAM requirements based on model architecture, GPU specs, and quantization format.