🎯 Memory & CPU planning tool for Weaviate vector database deployments
Beginner-friendly Estimator based on official Weaviate documentation to help you plan memory and CPU requirements for your vector database deployment.
- Memory: 2x GC overhead rule + HNSW connections (1.5x avg)
- CPU: Official formula
1000ms ÷ latency × 80% efficiency - Storage: Vector + metadata + 20% overhead
- All compression types: PQ, BQ, SQ, RQ 8-bit, RQ 1-bit
- Performance-based: Uses target QPS + expected latency
- Compression comparison: Side-by-side memory savings
- Deployment recommendations: Docker → Kubernetes based on scale
- Optimization tips: Automatic suggestions for your config
| Method | Memory Saved | Training | Best For |
|---|---|---|---|
| PQ | 85% | ✅ | Best balance |
| BQ | 97% | ❌ | Maximum savings |
| SQ | 75% | ✅ | Fast compression |
| RQ 8-bit | 75% | ❌ | No training, 8-bit |
| RQ 1-bit | 97% | ❌ | No training, max savings |
Visit the live calculator - No installation needed!
# Clone and setup
git clone https://github.com/Shah91n/Weaviate-Memory-CPU-Calculator.git
cd Weaviate-Memory-CPU-Calculator
pip install -r requirements.txt
# Run locally
streamlit run streamlit_app.py
# Open: http://localhost:8501# Build and run
docker build -t weaviate-calculator .
docker run -p 8501:8501 weaviate-calculator# Vector memory (with 2x GC overhead)
vector_memory = objects × dimensions × 4 bytes × 2
# HNSW connections (1.5x average)
connections = objects × maxConnections × 1.5 × 10 bytes
# Total memory
total = vector_memory + connections# Official Weaviate formula
qps_per_core = 1000ms ÷ expected_latency_ms × 0.8
min_cores = target_qps ÷ qps_per_core
recommended = min_cores × 2 # Headroom for imports- Weaviate Disk Storage Calculator - Detailed disk planning
- Weaviate Disk Calculator Source - Open source
- Resource Planning - Core formulas
- Compression Guide - All methods
- Vector Quantization - Technical details
Found a bug or want to improve something? Contributions welcome!
MIT License - See LICENSE file for details
💡 Made for the Weaviate Users & community | Star ⭐ if this helped you!