diff --git a/README.md b/README.md
index b2c85dd..19f783e 100644
--- a/README.md
+++ b/README.md
@@ -378,7 +378,7 @@ Luxury food photograph of an italian Linguine pasta alle vongole dish with lots
 
 ### 🗜️ Quantization
 
-MFLUX supports running FLUX in 4-bit or 8-bit quantized mode. Running a quantized version can greatly speed up the
+MFLUX supports running FLUX in 3, 4, 6, or 8-bit quantized mode. Running a quantized version can greatly speed up the
 generation process and reduce the memory consumption by several gigabytes. [Quantized models also take up less disk space](#-size-comparisons-for-quantized-models).
 
 ```sh
@@ -404,11 +404,10 @@ running the 8-bit quantized version on this particular machine. Unlike the non-q
 
 The model sizes for both `schnell` and `dev` at various quantization levels are as follows:
 
-| 4 bit  | 8 bit   | Original (16 bit) |
-|--------|---------|-------------------|
-| 9.85GB | 18.16GB | 33.73GB           |
+| 3 bit  | 4 bit  | 6 bit   | 8 bit   | Original (16 bit) |
+|--------|--------|---------|---------|-------------------|
+| 7.52GB | 9.61GB | 13.81GB | 18.01GB | 33.73GB           |
 
-The reason weights sizes are not fully cut in half is because a small number of weights are not quantized and kept at full precision.
 
 #### 💾 Saving a quantized version to disk
 
diff --git a/src/mflux/ui/defaults.py b/src/mflux/ui/defaults.py
index 7ed4bd7..31a307f 100644
--- a/src/mflux/ui/defaults.py
+++ b/src/mflux/ui/defaults.py
@@ -7,4 +7,4 @@ MODEL_INFERENCE_STEPS = {
     "dev": 14,
     "schnell": 4,
 }
-QUANTIZE_CHOICES = [4, 8]
+QUANTIZE_CHOICES = [3, 4, 6, 8]
diff --git a/src/mflux/weights/quantization_util.py b/src/mflux/weights/quantization_util.py
index 3592f69..0afa685 100644
--- a/src/mflux/weights/quantization_util.py
+++ b/src/mflux/weights/quantization_util.py
@@ -21,12 +21,10 @@ class QuantizationUtil:
 
         if quantize is not None or q_level is not None:
             bits = int(q_level) if q_level is not None else quantize
-            # fmt: off
-            nn.quantize(vae, class_predicate=lambda _, m: isinstance(m, nn.Linear), group_size=64, bits=bits)
-            nn.quantize(transformer, class_predicate=lambda _, m: isinstance(m, nn.Linear) and len(m.weight[1]) > 64, group_size=64, bits=bits)
-            nn.quantize(t5_text_encoder, class_predicate=lambda _, m: isinstance(m, nn.Linear), group_size=64, bits=bits)
-            nn.quantize(clip_text_encoder, class_predicate=lambda _, m: isinstance(m, nn.Linear), group_size=64, bits=bits)
-            # fmt: on
+            nn.quantize(vae, bits=bits)
+            nn.quantize(transformer, bits=bits)
+            nn.quantize(t5_text_encoder, bits=bits)
+            nn.quantize(clip_text_encoder, bits=bits)
 
     @staticmethod
     def quantize_controlnet(
@@ -35,6 +33,7 @@ class QuantizationUtil:
         transformer_controlnet: nn.Module,
     ):
         q_level = weights.meta_data.quantization_level
+
         if quantize is not None or q_level is not None:
             bits = int(q_level) if q_level is not None else quantize
-            nn.quantize(transformer_controlnet, class_predicate=lambda _, m: isinstance(m, nn.Linear) and len(m.weight[1]) > 128, group_size=128, bits=bits)  # fmt: off
+            nn.quantize(transformer_controlnet, bits=bits)