Skip to content
HQ
HardwareHQ
Cloud PricingGPUsModels
Home/Edge AI Studio

Edge AI Studio

Match models to Jetson, Coral, and a few other boards. tok/s and tok/W are TOPS/RAM heuristics.

Limited data: 9 devices and 5 SLMs. tok/s and tok/W are TOPS/RAM heuristics. Phone NPUs are not in this picker.

In plain English: check whether a Jetson, Coral, or other listed board can run your model.

RAM Usage
0.7GB required16GB available
Comfortable4% utilization
Compatibility
Compatible
Est. Speed
100 tok/s
Efficiency
4.00 tok/W
Power Draw
25W
Good for real-time inference at 100 tok/s (4.00 tok/W).

Ready to deploy?

Check detailed hardware specs and find the right edge device for your deployment.

GPU DatabaseQuantization Guide

Also

Live cloud pricesInstance tape from the live feedGPU catalogSpecs for the unique catalogModel catalogParams and estimated VRAMGPU comparisonSide-by-side catalog specs
HQ
HardwareHQ

Live cloud GPU prices, catalog specs, and fit estimates. Free. No signup.

Market

  • Cloud GPU Pricing
  • Buy vs Rent
  • Inference Calculator
  • Training Calculator
  • VRAM Calculator

Catalog

  • GPU catalog
  • Model catalog
  • GPU Comparison
  • Compatibility Matrix
  • AI Benchmarks
  • Model Finder

Planning studios

  • Research Studio
  • RAG Studio
  • Creative Studio
  • Coding Studio
  • Edge AI Studio
  • Hardware Architect
  • Topology Lab

Reference

  • LLM Requirements
  • Quantization Guide
  • Best GPU for LLaMA
  • Best GPU for DeepSeek
  • Best GPU for Stable Diffusion
  • Best GPU for Mistral
  • Best GPU for Qwen
  • Best GPU for Phi
  • Best GPU for Gemma
  • AI Homelab Guide

Company

  • About
  • Contact
  • Advertise
  • Privacy Policy
  • Terms of Service

© 2026 HardwareHQ. All rights reserved.

@HardwareHQio