diff --git a/invokeai/backend/quantization/__init__.py b/invokeai/backend/quantization/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/invokeai/backend/quantization/fast_quantized_diffusion_model.py b/invokeai/backend/quantization/fast_quantized_diffusion_model.py
index 65b64a69a1..6ad82b8e9e 100644
--- a/invokeai/backend/quantization/fast_quantized_diffusion_model.py
+++ b/invokeai/backend/quantization/fast_quantized_diffusion_model.py
@@ -14,7 +14,7 @@ from diffusers.utils import (
 from optimum.quanto.models import QuantizedDiffusersModel
 from optimum.quanto.models.shared_dict import ShardedStateDict
 
-from invokeai.backend.requantize import requantize
+from invokeai.backend.quantization.requantize import requantize
 
 
 class FastQuantizedDiffusersModel(QuantizedDiffusersModel):
diff --git a/invokeai/backend/quantization/fast_quantized_transformers_model.py b/invokeai/backend/quantization/fast_quantized_transformers_model.py
index 72636a43fb..b811b598e7 100644
--- a/invokeai/backend/quantization/fast_quantized_transformers_model.py
+++ b/invokeai/backend/quantization/fast_quantized_transformers_model.py
@@ -9,7 +9,7 @@ from transformers.modeling_utils import get_checkpoint_shard_files, load_state_d
 from transformers.models.auto import AutoModelForTextEncoding
 from transformers.utils import SAFE_WEIGHTS_INDEX_NAME, SAFE_WEIGHTS_NAME, is_accelerate_available
 
-from invokeai.backend.requantize import requantize
+from invokeai.backend.quantization.requantize import requantize
 
 
 class FastQuantizedTransformersModel(QuantizedTransformersModel):
diff --git a/invokeai/backend/requantize.py b/invokeai/backend/quantization/requantize.py
similarity index 100%
rename from invokeai/backend/requantize.py
rename to invokeai/backend/quantization/requantize.py