What is Quantisation?
Verified 5 August 2026
A 768-dimensional float32 vector occupies about 3 KB. Quantising to int8 cuts that to 768 bytes; binary quantisation, which stores only the sign of each dimension, cuts it to 96 bytes — a 32× reduction either way.
The precision loss is real but recoverable. The standard pattern is a two-stage search: retrieve a generous candidate set using the cheap binary codes, then rerank that much smaller set with higher-precision vectors. Recall approaches the uncompressed baseline at a fraction of the memory.
Common questions
What is Quantisation?
Quantisation compresses vectors by storing each dimension in fewer bits, cutting memory and speeding comparison at a small cost in precision.
How does Quantisation work in practice?
The precision loss is real but recoverable. The standard pattern is a two-stage search: retrieve a generous candidate set using the cheap binary codes, then rerank that much smaller set with higher-precision vectors. Recall approaches the uncompressed baseline at a fraction of the memory.
See it working
The free tier is 10,000 requests a month with no card — enough to test any of this against your own queries.