diff --git a/CHANGELOG.md b/CHANGELOG.md
index fee7f76b..456e0a9c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -10,6 +10,9 @@
 
 ### Changed
 
+- **Evaluations Vacuum Strategy**: `populate_db` now uses periodic vacuum to prevent disk exhaustion with large datasets
+  - Disables auto_vacuum during population, vacuums every 100 documents with retention=0
+  - Prevents disk space issues when building databases with thousands of documents (e.g., HotpotQA)
 - **Benchmarks Documentation**: Restructured benchmarks.md for clarity
   - Added dedicated Methodology section explaining MRR, MAP, and QA Accuracy metrics
   - Organized results by dataset with retrieval and QA subsections
diff --git a/evaluations/evaluations/benchmark.py b/evaluations/evaluations/benchmark.py
index b6d260b8..cb689e55 100644
--- a/evaluations/evaluations/benchmark.py
+++ b/evaluations/evaluations/benchmark.py
@@ -75,9 +75,14 @@ async def populate_db(
     if spec.document_limit is not None:
         corpus = corpus.select(range(min(spec.document_limit, len(corpus))))
 
+    # Disable auto_vacuum - we'll vacuum periodically instead to prevent disk exhaustion
+    config.storage.auto_vacuum = False
+    vacuum_interval = 100
+
     with Progress() as progress:
         task = progress.add_task("[green]Populating database...", total=len(corpus))
         async with HaikuRAG(db, config=config) as rag:
+            docs_since_vacuum = 0
             for doc in corpus:
                 doc_mapping = cast(Mapping[str, Any], doc)
                 payload = spec.document_mapper(doc_mapping)
@@ -101,8 +106,17 @@ async def populate_db(
                     metadata=payload.metadata,
                     format=payload.format,
                 )
+                docs_since_vacuum += 1
                 progress.advance(task)
 
+                # Periodic vacuum to prevent disk exhaustion
+                if docs_since_vacuum >= vacuum_interval:
+                    await rag.store.vacuum(retention_seconds=0)
+                    docs_since_vacuum = 0
+
+            # Final vacuum
+            await rag.store.vacuum(retention_seconds=0)
+
 
 async def run_retrieval_benchmark(
     spec: DatasetSpec,