Qwen Embedding / Qwen3 Embedding 8B
Distillation for Qwen3 Embedding 8B
The published profile is indicative; engineering measurements are completed for the selected model and hardware.
Before → After
Base releaseVerified checkpoint
8.000B
8.000B
DistillationTeacher / Student
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 and certified results are delivered with the project.
Runtime packagingsentence-transformers, transformers