LaBSE Ru Turbo vs Rubert Tiny Turbo

Wins 0 of 0 benchmarks
Wins 0 of 0 benchmarks
No benchmarks in this slice.

Specs

SpecLaBSE Ru TurboRubert Tiny Turbo
Context1K2K
WeightsOpenOpen
ReleasedJun 2024Jun 2024
Dimensions768312
Max input1K tokens2K tokens
Languagesruru
Memory (4-bit)0.1 GB0 GB
LicenceMITMIT
Commercial useAllowedAllowed

What breaks when you switch

LaBSE Ru Turbo → Rubert Tiny Turbo
Re-embed your whole corpus›

Vectors from different models can't be mixed; dimensions change from 768 to 312.

Rubert Tiny Turbo → LaBSE Ru Turbo
Re-embed your whole corpus›

Vectors from different models can't be mixed; dimensions change from 312 to 768.

Max input: 2K tokens → 1K tokens
Memory (4-bit): 0 GB → 0.1 GB