AI Decision System
Replayable, offline-verifiable records for AI-assisted go/no-go decisions: experiment promotions, typed model answers and human-approved actions.
翻译准备中
尚未检测到更新。GitHub 发布版本后会显示在这里。
个人 GitHub 账号下公开仓库的所有者可以登录并验证所有权,自行管理介绍,无需管理员批准。
登录并生成验证文件,在 30 分钟内将其提交到此仓库的默认分支。其他分支或分叉仓库中的文件无效。然后在下方检查文件,即可无需管理员批准直接管理项目。请保留文件以维持管理权限。
如需登录,将前往登录页面。登录后请回到此处,再次点击所选的验证按钮。
在项目文件夹中运行 /nomorevibe verify,即可验证所有权并自行管理介绍。
一分钟完成验证Estimate LLM VRAM — model weights, KV cache, context window & concurrent users — and find the right GPU. Live Hugging Face data, runs in your browser.
翻译准备中
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
How much GPU memory does an LLM actually need — and what runs it?
A fast, client-side calculator that models the terms params × 2 misses, and
names every assumption it makes.
🔗 tahircengiz.github.io/LLMScale — no account, no backend, no install.
In Turkish: /tr/.
Architecture is pulled live from the Hugging Face Hub. Gated repos (Llama,
Gemma, Mistral) can't be read from a browser, so their configs ship in a bundled
database alongside a curated preset list. Repos with no config of their own —
GGUF forks, for instance — are resolved through their base_model lineage, and
the page says so.查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
How much GPU memory does an LLM actually need — and what runs it?
A fast, client-side calculator that models the terms params × 2 misses, and
names every assumption it makes.
🔗 tahircengiz.github.io/LLMScale — no account, no backend, no install.
In Turkish: /tr/.
Architecture is pulled live from the Hugging Face Hub. Gated repos (Llama,
Gemma, Mistral) can't be read from a browser, so their configs ship in a bundled
database alongside a curated preset list. Repos with no config of their own —
GGUF forks, for instance — are resolved through their base_model lineage, and
the page says so.查看完整 README ↗