diff --git a/docs/docs/frigate/hardware.md b/docs/docs/frigate/hardware.md
index ea387625f..aa3e4044e 100644
--- a/docs/docs/frigate/hardware.md
+++ b/docs/docs/frigate/hardware.md
@@ -180,12 +180,12 @@ Inference speeds will vary greatly depending on the GPU and the model used.
 ✅ - Accelerated with CUDA Graphs
 ❌ - Not accelerated with CUDA Graphs
 
-| Name            | ✅ YOLOv9 Inference Time  | ✅ RF-DETR Inference Time | ❌ YOLO-NAS Inference Time 
-| --------------- | ------------------------ | ------------------------- | -------------------------- |
-| RTX 3050        | t-320: 8 ms s-320: 10 ms | Nano-320: ~ 12 ms         | 320: ~ 10 ms 640: ~ 16 ms  |
-| RTX 3070        | t-320: 6 ms s-320: 8 ms  | Nano-320: ~ 9 ms          | 320: ~ 8 ms 640: ~ 14 ms   |
-| RTX A4000       |                          |                           | 320: ~ 15 ms               |
-| Tesla P40       |                          |                           | 320: ~ 105 ms              |
+| Name            | ✅ YOLOv9 Inference Time  | ✅ RF-DETR Inference Time | ❌ YOLO-NAS Inference Time |
+| --------------- | ------------------------------------- | ------------------------- | --------------------------- |
+| RTX 3050        | t-320: 8 ms s-320: 10 ms s-640: 28 ms | Nano-320: ~ 12 ms         | 320: ~ 10 ms 640: ~ 16 ms   |
+| RTX 3070        | t-320: 6 ms s-320: 8 ms s-640: 25 ms  | Nano-320: ~ 9 ms          | 320: ~ 8 ms 640: ~ 14 ms    |
+| RTX A4000       |                                       |                           | 320: ~ 15 ms                |
+| Tesla P40       |                                       |                           | 320: ~ 105 ms               |
 
 ### Apple Silicon
 
@@ -197,10 +197,11 @@ Apple Silicon can not run within a container, so a ZMQ proxy is utilized to comm
 
 :::
 
-| Name      | YOLOv9 Inference Time  |
-| --------- | ---------------------- |
-| M3 Pro    | t-320: 6 ms s-320: 8ms |
-| M1        | s-320: 9ms             |
+| Name      | YOLOv9 Inference Time                |
+| --------- | ------------------------------------ |
+| M4        | s-20: 10 ms                          |
+| M3 Pro    | t-320: 6 ms s-320: 8 ms s-640: 20 ms |
+| M1        | s-320: 9ms                           |
 
 ### ROCm - AMD GPU
 
@@ -234,7 +235,7 @@ The MX3 is a pipelined architecture, where the maximum frames per second support
 | YOLOv9s              | 640        | ~ 41 ms            | ~ 110         |
 | YOLOX-Small          | 640        | ~ 16 ms            | ~ 263         |
 | SSDlite MobileNet v2 | 320        | ~ 5 ms             | ~ 1056        |
-    
+
 Inference speeds may vary depending on the host platform. The above data was measured on an **Intel 13700 CPU**. Platforms like Raspberry Pi, Orange Pi, and other ARM-based SBCs have different levels of processing capability, which may limit total FPS.
 
 ### Nvidia Jetson
diff --git a/frigate/detectors/plugins/hailo8l.py b/frigate/detectors/plugins/hailo8l.py
index aa856dd80..cafc809c9 100755
--- a/frigate/detectors/plugins/hailo8l.py
+++ b/frigate/detectors/plugins/hailo8l.py
@@ -33,10 +33,6 @@ def preprocess_tensor(image: np.ndarray, model_w: int, model_h: int) -> np.ndarr
         image = image[0]
 
     h, w = image.shape[:2]
-
-    if (w, h) == (320, 320) and (model_w, model_h) == (640, 640):
-        return cv2.resize(image, (model_w, model_h), interpolation=cv2.INTER_LINEAR)
-
     scale = min(model_w / w, model_h / h)
     new_w, new_h = int(w * scale), int(h * scale)
     resized_image = cv2.resize(image, (new_w, new_h), interpolation=cv2.INTER_CUBIC)
diff --git a/frigate/util/object.py b/frigate/util/object.py
index d9a8c2f71..905745da6 100644
--- a/frigate/util/object.py
+++ b/frigate/util/object.py
@@ -269,7 +269,20 @@ def is_object_filtered(obj, objects_to_track, object_filters):
 
 def get_min_region_size(model_config: ModelConfig) -> int:
     """Get the min region size."""
-    return max(model_config.height, model_config.width)
+    largest_dimension = max(model_config.height, model_config.width)
+
+    if largest_dimension > 320:
+        # We originally tested allowing any model to have a region down to half of the model size
+        # but this led to many false positives. In this case we specifically target larger models
+        # which can benefit from a smaller region in some cases to detect smaller objects.
+        half = int(largest_dimension / 2)
+
+        if half % 4 == 0:
+            return half
+
+        return int((half + 3) / 4) * 4
+
+    return largest_dimension
 
 
 def create_tensor_input(frame, model_config: ModelConfig, region):