Before → After
Base releaseVerified checkpoint
355.000B
355.000B
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 packagingsglang, transformers