LOCAL AI · MEMORY
LLM VRAM Calculator
Estimate GPU memory by model, quantization and context length.
InputsModel · quantization · context
AI memory & cost tools
Plan your AI workload,
see the numbers.
Estimate local AI memory, API caching and document embedding costs for your workload.
Available tools
3 toolsAPI · COST COMPARISON
Claude Cache Calculator
Compare no caching, 5-minute caching and 1-hour caching for repeated requests.
InputsModel · tokens · request interval
RAG · EMBEDDING COST
RAG Embedding Calculator
See how chunk overlap changes token usage, initial costs and monthly re-embedding costs.
InputsDocuments · chunks · overlap · rate
Clear results. Clear assumptions.
Calculation & verification standards- Set your own conditions
- Adjust the inputs to match your workload.
- See how it is calculated
- Check the units, assumptions and official sources.
- Estimates stay separate from measurements
- Unverified values are never presented as measurements.