The AI hardware
database & decision engine
Compare 874+ GPUs, check if your hardware can run any AI model, and track live cloud GPU pricing from 24+ providers — like Tom's Hardware, built for AI.
Not sure if your GPU can run a model? Check compatibility instantly ↓
Instant Compatibility Check
Can your GPU run this model?
Select a GPU and AI model to check VRAM compatibility instantly.
Quick compatibility check
Popular Checks
Popular compatibility checks
All checksLive Database
LiveReal-time GPU market data
Current GPU MSRPs and cheapest cloud instances — pulled from our live database, updated continuously.
Calculators & Tools
Database-powered calculators
Every calculator runs on live data — real GPU specs, real cloud prices, real model benchmarks. Free, no signup.
Cloud GPU Market Tracker
Live pricing from 24+ providers. Filter by GPU, VRAM, compliance, and availability.
VRAM Calculator
Estimate GPU memory requirements at every quantization level for any model.
Inference Cost Estimator
Self-hosted vs API: cost-per-token, throughput, and break-even analysis.
GPU Comparison
Side-by-side specs, benchmarks, and pricing for consumer through enterprise GPUs.
Model Finder
Search 289+ AI models by capability, size, license, and hardware requirements.
Compatibility Lab
Full GPU × Model compatibility matrix with quantization-aware VRAM estimates.
Advanced Planning
Planning studios powered by the database
Go beyond specs. Each studio uses live database data to simulate real workloads — plan training runs, architect RAG pipelines, and validate hardware before spending a dollar.
Research Studio
Simulate training runs, fine-tuning jobs, and LoRA experiments. Get VRAM estimates before committing compute.
RAG Studio
Architect retrieval pipelines end-to-end. Size vector indexes, select embedding models, and plan LLM inference hardware.
Creative Studio
Plan image and video generation workloads. Resolution scaling, batch processing, and workstation sizing for agencies.
Coding Studio
Match AI coding assistants to your hardware. HumanEval benchmarks, VRAM requirements, and context window analysis.
Hardware Architect
Design complete AI workstations from budget and use case. Exportable bill of materials with sourcing links.
Cost Analysis Engine
Full TCO modeling: rent vs buy, electricity, depreciation, utilization curves, and break-even analysis.
Edge AI Studio
Plan IoT and embedded deployments. Compare Jetson, Coral, and mobile chips with tokens-per-watt efficiency metrics.
Topology Lab
Plan PCIe lane allocation, detect multi-GPU conflicts, and optimize interconnect bandwidth for multi-card setups.
Hardware Guides
GPU buying guides
Recommendations backed by real VRAM data and benchmark analysis.
Stay informed
Weekly AI hardware brief
GPU price movements, new model releases, cloud pricing changes, and hardware availability — one email, every Monday.