272 lines
10 KiB
HTML
272 lines
10 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<title>Model Library — Nexus One AI Portal</title>
|
|
<link rel="stylesheet" href="style.css?v=4">
|
|
</head>
|
|
<body>
|
|
|
|
<header class="topnav">
|
|
<a href="index.html" class="brand">Nexus One <span>AI</span></a>
|
|
<nav>
|
|
<a href="index.html">Home</a>
|
|
<a href="quickstart.html">Quick Start</a>
|
|
<a href="prompts.html">Prompt Library</a>
|
|
<a href="usecases.html">Use Cases</a>
|
|
<div class="nav-dropdown">
|
|
<button class="nav-drop-btn active">Help ▾</button>
|
|
<div class="nav-drop-menu">
|
|
<span class="nav-drop-cat">LEARN /</span>
|
|
<a href="quickstart.html">Quick Start</a>
|
|
<a href="models.html" class="active">Models</a>
|
|
<span class="nav-drop-cat">SUPPORT /</span>
|
|
<a href="troubleshooting.html">Troubleshoot</a>
|
|
<a href="faq.html">FAQ</a>
|
|
<span class="nav-drop-cat">MORE /</span>
|
|
<a href="glossary.html">Glossary</a>
|
|
<a href="whats-new.html">What's New</a>
|
|
</div>
|
|
</div>
|
|
<div class="nav-dropdown">
|
|
<button class="nav-drop-btn">Admin ▾</button>
|
|
<div class="nav-drop-menu nav-drop-menu-wide">
|
|
<span class="nav-drop-cat">DOCS /</span>
|
|
<a href="security.html">Security & Privacy</a>
|
|
<a href="admin.html">Admin Guide</a>
|
|
<span class="nav-drop-cat">MONITOR /</span>
|
|
<a href="dashboard.html">Dashboard</a>
|
|
<a href="analytics.html">Usage Analytics</a>
|
|
<a href="audit.html">Audit Log</a>
|
|
<a href="feedback.html">Feedback & Ratings</a>
|
|
<span class="nav-drop-cat">MANAGE /</span>
|
|
<a href="users.html">Users</a>
|
|
<a href="teams.html">Teams</a>
|
|
<a href="models-admin.html">Model Manager</a>
|
|
<a href="training.html">Training</a>
|
|
<a href="knowledge.html">Knowledge Base</a>
|
|
<span class="nav-drop-cat">TOOLS /</span>
|
|
<a href="apikeys.html">API Keys</a>
|
|
<a href="benchmark.html">Benchmarking</a>
|
|
<a href="model-compare.html">Model Compare</a>
|
|
<a href="api-playground.html">API Playground</a>
|
|
<a href="guardrails.html">Guardrails</a>
|
|
<a href="rag-quality.html">RAG Quality</a>
|
|
<a href="router.html">Model Router</a>
|
|
<a href="connectors.html">Connectors</a>
|
|
<span class="nav-drop-cat">SYSTEM /</span>
|
|
<a href="console.html">Console</a>
|
|
<a href="settings.html">Settings</a>
|
|
</div>
|
|
</div>
|
|
<div class="nav-dropdown">
|
|
<button class="nav-drop-btn">AI Tools ▾</button>
|
|
<div class="nav-drop-menu">
|
|
<span class="nav-drop-cat">INTELLIGENCE /</span>
|
|
<a href="documents.html">Document Intelligence</a>
|
|
<a href="chat-multi.html">Multimodal Chat</a>
|
|
<a href="prompt-studio.html">Prompt Studio</a>
|
|
<a href="meeting.html">Meeting Assistant</a>
|
|
<span class="nav-drop-cat">AUTOMATION /</span>
|
|
<a href="agents.html">Agent Builder</a>
|
|
<a href="schedules.html">Scheduled Jobs</a>
|
|
<a href="workflows.html">Workflow Automation</a>
|
|
<span class="nav-drop-cat">QUALITY /</span>
|
|
<a href="evals.html">AI Eval Suite</a>
|
|
<a href="chatrooms.html">Chat Rooms</a>
|
|
</div>
|
|
</div>
|
|
</nav>
|
|
<a href="notifications.html" style="position:relative">🔔</a>
|
|
<span class="badge" data-brand="tier">Basic Tier</span>
|
|
<div id="nav-org-logo" class="nav-org-logo"></div>
|
|
</header>
|
|
|
|
<div class="page-hero">
|
|
<div class="label">Model Library</div>
|
|
<h1>AI Models on Your System</h1>
|
|
<p>All models run entirely on your server — no internet required, no per-query cost. Choose the right one for your task.</p>
|
|
</div>
|
|
|
|
<div class="content">
|
|
|
|
<div class="notice" style="margin-bottom:32px">
|
|
💡 To use a model, open <a href="http://ai.local:3001" target="_blank">Open WebUI</a> and select it from the model dropdown at the top of the chat. You can switch models at any time without losing your conversation.
|
|
</div>
|
|
|
|
<!-- CHAT MODELS -->
|
|
<div class="section-title">Chat & Reasoning Models</div>
|
|
|
|
<div class="model-table">
|
|
<div class="mt-header">
|
|
<div>Model</div>
|
|
<div>Best for</div>
|
|
<div>Speed</div>
|
|
<div>VRAM</div>
|
|
<div>Context</div>
|
|
</div>
|
|
|
|
<div class="mt-row recommended">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">llama3.1:8b</div>
|
|
<div class="mt-badge">Recommended — start here</div>
|
|
</div>
|
|
<div class="mt-cell">General Q&A, document chat, writing, summarising</div>
|
|
<div class="mt-cell"><span class="speed-bar s4"></span> Very Fast</div>
|
|
<div class="mt-cell">~5 GB</div>
|
|
<div class="mt-cell">128K tokens</div>
|
|
</div>
|
|
|
|
<div class="mt-row">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">llama3.2:3b</div>
|
|
<div class="mt-sub">Lightweight</div>
|
|
</div>
|
|
<div class="mt-cell">Quick lookups, simple questions, high-concurrency use</div>
|
|
<div class="mt-cell"><span class="speed-bar s5"></span> Fastest</div>
|
|
<div class="mt-cell">~2 GB</div>
|
|
<div class="mt-cell">128K tokens</div>
|
|
</div>
|
|
|
|
<div class="mt-row">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">mistral:7b</div>
|
|
<div class="mt-sub">Reasoning</div>
|
|
</div>
|
|
<div class="mt-cell">Structured tasks, code, logical reasoning, JSON extraction</div>
|
|
<div class="mt-cell"><span class="speed-bar s4"></span> Very Fast</div>
|
|
<div class="mt-cell">~5 GB</div>
|
|
<div class="mt-cell">32K tokens</div>
|
|
</div>
|
|
|
|
<div class="mt-row">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">llama3.1:70b</div>
|
|
<div class="mt-sub">High accuracy</div>
|
|
</div>
|
|
<div class="mt-cell">Complex reasoning, legal/technical analysis, nuanced writing</div>
|
|
<div class="mt-cell"><span class="speed-bar s2"></span> Slower</div>
|
|
<div class="mt-cell">~42 GB</div>
|
|
<div class="mt-cell">128K tokens</div>
|
|
</div>
|
|
|
|
<div class="mt-row">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">gemma2:9b</div>
|
|
<div class="mt-sub">Efficient</div>
|
|
</div>
|
|
<div class="mt-cell">Instruction following, structured outputs, multilingual</div>
|
|
<div class="mt-cell"><span class="speed-bar s4"></span> Very Fast</div>
|
|
<div class="mt-cell">~6 GB</div>
|
|
<div class="mt-cell">8K tokens</div>
|
|
</div>
|
|
|
|
<div class="mt-row">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">phi3:mini</div>
|
|
<div class="mt-sub">Microsoft</div>
|
|
</div>
|
|
<div class="mt-cell">Simple tasks, drafting, lightweight deployments</div>
|
|
<div class="mt-cell"><span class="speed-bar s5"></span> Fastest</div>
|
|
<div class="mt-cell">~2.3 GB</div>
|
|
<div class="mt-cell">128K tokens</div>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<!-- EMBEDDING MODELS -->
|
|
<div class="section-title" style="margin-top:40px">Embedding Models</div>
|
|
<div class="notice" style="margin-bottom:20px">Embedding models don't generate text — they convert documents and queries into numbers (vectors) that ChromaDB uses for semantic search. You don't select these in chat; they run automatically when you upload documents.</div>
|
|
|
|
<div class="model-table">
|
|
<div class="mt-header">
|
|
<div>Model</div>
|
|
<div>Best for</div>
|
|
<div>Dimensions</div>
|
|
<div>VRAM</div>
|
|
<div></div>
|
|
</div>
|
|
|
|
<div class="mt-row recommended">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">nomic-embed-text</div>
|
|
<div class="mt-badge">Default for RAG</div>
|
|
</div>
|
|
<div class="mt-cell">General document search and Q&A</div>
|
|
<div class="mt-cell">768</div>
|
|
<div class="mt-cell">~270 MB</div>
|
|
<div class="mt-cell"></div>
|
|
</div>
|
|
|
|
<div class="mt-row">
|
|
<div class="mt-cell">
|
|
<div class="mt-name">mxbai-embed-large</div>
|
|
<div class="mt-sub">Higher accuracy</div>
|
|
</div>
|
|
<div class="mt-cell">Better retrieval accuracy for complex technical documents</div>
|
|
<div class="mt-cell">1024</div>
|
|
<div class="mt-cell">~670 MB</div>
|
|
<div class="mt-cell"></div>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<!-- CHOOSING GUIDE -->
|
|
<div class="section-title" style="margin-top:40px">Which model should I use?</div>
|
|
<div class="choose-grid">
|
|
|
|
<div class="choose-card">
|
|
<div class="choose-task">💬 Everyday chat and Q&A</div>
|
|
<div class="choose-model">llama3.1:8b</div>
|
|
<div class="choose-reason">Fast enough to feel instant, capable enough for most office tasks.</div>
|
|
</div>
|
|
|
|
<div class="choose-card">
|
|
<div class="choose-task">📂 Chat with documents</div>
|
|
<div class="choose-model">llama3.1:8b</div>
|
|
<div class="choose-reason">Large 128K context window means it can read long documents in one go.</div>
|
|
</div>
|
|
|
|
<div class="choose-card">
|
|
<div class="choose-task">⚡ High concurrent users</div>
|
|
<div class="choose-model">llama3.2:3b</div>
|
|
<div class="choose-reason">Very low VRAM footprint means more users can be served simultaneously.</div>
|
|
</div>
|
|
|
|
<div class="choose-card">
|
|
<div class="choose-task">🧠 Complex analysis</div>
|
|
<div class="choose-model">llama3.1:70b</div>
|
|
<div class="choose-reason">Significantly more accurate for nuanced reasoning, legal, and technical work. Slower.</div>
|
|
</div>
|
|
|
|
<div class="choose-card">
|
|
<div class="choose-task">💻 Code generation</div>
|
|
<div class="choose-model">mistral:7b</div>
|
|
<div class="choose-reason">Strong at structured outputs, JSON, SQL, Python, and logical step-by-step tasks.</div>
|
|
</div>
|
|
|
|
<div class="choose-card">
|
|
<div class="choose-task">🌐 Multilingual tasks</div>
|
|
<div class="choose-model">gemma2:9b</div>
|
|
<div class="choose-reason">Good multilingual coverage for Indian regional languages and English.</div>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="notice" style="margin-top:32px">
|
|
💡 <strong>Context window explained:</strong> The context window is how much text the model can read at once. 128K tokens ≈ about 90,000 words — enough for most full documents. If your document is very large, split it into sections or use ChromaDB to chunk and search it automatically.
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<footer>
|
|
<p>Nexus One AI · Powered by Cezen · Basic Tier</p>
|
|
<p>Questions? <a href="mailto:support@cezentech.com">support@cezentech.com</a> · <a href="https://cezentech.com" target="_blank">cezentech.com</a></p>
|
|
</footer>
|
|
|
|
<script src="auth.js"></script>
|
|
<script src="branding.js"></script>
|
|
</body>
|
|
</html>
|