← Agent Data Hub · Search endpoints · /llms.txt

Vector Database HNSW Index RAM & Disk Storage Sizing Calculator

Calculates exact RAM and disk requirements for storing millions of vector embeddings (768d, 1536d, 3072d) across FP32, FP16, INT8 scalar, and Binary quantization.

Call it (no API key)

GET https://api.agentdatahub.de/api/v1/call/dev-vector-db-ram-calculator?vectors_count=1000000&dimensions=1536&compact=1

Full metadata: without compact=1 · Markdown: format=llm · Only some fields: add &fields=a,b.c · MCP: tool call_api with {"apiId":"dev-vector-db-ram-calculator"}

Parameters

Example response (live, compact)

{
  "apiId": "dev-vector-db-ram-calculator",
  "data_freshness": "cached",
  "data": {
    "vectors_count": 1000000,
    "dimensions": 1536,
    "ram_required_gb": {
      "fp32_uncompressed_gb": 7.07,
      "fp16_half_precision_gb": 3.53,
      "int8_scalar_quantized_gb": 1.77,
      "binary_quantized_gb": 0.22
    }
  },
  "source": "100% Platform AI Infrastructure Sizing Engine",
  "license": "100% Platform Owned Compute"
}

Source & license