BGE / BGE-M3
BF16 quantization for BGE-M3
The published profile is indicative; engineering measurements are completed for the selected model and hardware.
Before → After
Base releaseVerified checkpoint
0.568B
0.568B
QuantizationBF16
Quality retention target
Quality retention target
Production artifactArtifact
Lineage and benchmark report
Lineage and benchmark report
GPU targeting
Weights and KV cacheEstimated until measured during engineering
Estimated VRAMMeasured
Runtime packagingsentence-transformers, transformers
Transparent pricing
Not currently orderable