Find yourperfect runtime
Answer three questions about your hardware, deployment target, and use case get an exact model size, framework, and one line install command, ready to copy.
4sizes
E2B · E4B · 26B · 31B
1
Hardware / Deployment Target
📱 Android / iOS Phone≤8 GB RAM
🍓 Raspberry Pi / SBC4–8 GB RAM
💻 Laptop / MacBook8–32 GB RAM
🖥️ Workstation GPURTX 3090 / 4090
🗄️ Server / Cloud GPUA100 · H100 · TPU
🤖 NVIDIA JetsonOrin Nano / AGX
💬 Chat / Assistant
⌨️ Code Generation
👁️ Vision / Multimodal
🔍 RAG / Long Context
🤖 Agentic Workflows
🎛️ Fine-tuning / Research
⚡ Speed / Low Latency
🏆 Maximum Quality
⚖️ Balanced
💾 Minimal Memory
Model
Params
Active
Context
Architecture
Min VRAM
Vision
Thinking
Fn Calling
Best For
⬇ Download Report (.txt)
⬇ Save This Tool (.html)
📋 Copy Setup Script