diff --git a/src/instructlab/sdg/utils/chunkers.py b/src/instructlab/sdg/utils/chunkers.py
index 8831bde6..8946b8b7 100644
--- a/src/instructlab/sdg/utils/chunkers.py
+++ b/src/instructlab/sdg/utils/chunkers.py
@@ -213,6 +213,8 @@ def chunk_documents(self) -> List:
 
         model_artifacts_path = StandardPdfPipeline.download_models_hf()
         pipeline_options = PdfPipelineOptions(artifacts_path=model_artifacts_path)
+        # Keep OCR models on the CPU instead of GPU
+        pipeline_options.ocr_options.use_gpu = False
         converter = DocumentConverter(
             format_options={
                 InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)