diff --git a/qdrant-landing/content/articles/bulk-uploads-in-qdrant.md b/qdrant-landing/content/articles/bulk-uploads-in-qdrant.md index 1625295eb..976b77ad7 100644 --- a/qdrant-landing/content/articles/bulk-uploads-in-qdrant.md +++ b/qdrant-landing/content/articles/bulk-uploads-in-qdrant.md @@ -251,4 +251,4 @@ The safest approach is to choose the right strategy for the workload instead of > **Tip:** After a large upload, confirm the collection status is green and the optimizers have finished before serving production traffic. -By designing the collection and upload process before ingestion starts, you can make bulk uploads more efficient, more stable, and easier to scale as your dataset grows. To size your deployment, use the [Qdrant sizing calculator](https://sizing.qdrant.tech). +By designing the collection and upload process before ingestion starts, you can make bulk uploads more efficient, more stable, and easier to scale as your dataset grows. To size your deployment, use the [Qdrant sizing calculator](https://sizing.qdrant.tech/estimate). diff --git a/qdrant-landing/content/documentation/scaling/vertical-scaling.md b/qdrant-landing/content/documentation/scaling/vertical-scaling.md index 08822a1d4..98268d2e4 100644 --- a/qdrant-landing/content/documentation/scaling/vertical-scaling.md +++ b/qdrant-landing/content/documentation/scaling/vertical-scaling.md @@ -48,6 +48,10 @@ num_vectors * dimensions * 4 bytes * 1.5 Quantization can reduce this estimate by a factor of 4 to 32, depending on the quantization method. + + On top of the vector data itself, budget for the HNSW index, which typically adds 20% to 30% overhead, along with payload indexes and the write-ahead log. Reserve about 20% headroom for optimizer operations and operating system cache. See [Quantization](/documentation/manage-data/quantization/) for the tradeoffs between quantization methods, and monitor actual memory usage before and after resizing (see [Monitor Collection Memory Usage](/documentation/ops-monitoring/memory-usage/)).