diff --git a/gpt4all-bindings/python/gpt4all/_pyllmodel.py b/gpt4all-bindings/python/gpt4all/_pyllmodel.py
index 284d8ab3..4c52a5b1 100644
--- a/gpt4all-bindings/python/gpt4all/_pyllmodel.py
+++ b/gpt4all-bindings/python/gpt4all/_pyllmodel.py
@@ -6,6 +6,7 @@ import platform
 import re
 import subprocess
 import sys
+import textwrap
 import threading
 from enum import Enum
 from queue import Queue
@@ -28,6 +29,16 @@ if TYPE_CHECKING:
 EmbeddingsType = TypeVar('EmbeddingsType', bound='list[Any]')
 
 
+# Detect Rosetta 2
+if platform.system() == "Darwin" and platform.processor() == "i386":
+    if subprocess.run(
+        "sysctl -n sysctl.proc_translated".split(), check=True, capture_output=True, text=True,
+    ).stdout.strip() == "1":
+        raise RuntimeError(textwrap.dedent("""\
+            Running GPT4All under Rosetta is not supported due to CPU feature requirements.
+            Please install GPT4All in an environment that uses a native ARM64 Python interpreter.
+        """))
+
 # Find CUDA libraries from the official packages
 cuda_found = False
 if platform.system() in ('Linux', 'Windows'):
diff --git a/gpt4all-bindings/python/setup.py b/gpt4all-bindings/python/setup.py
index 85dbe8ab..4c9c48e1 100644
--- a/gpt4all-bindings/python/setup.py
+++ b/gpt4all-bindings/python/setup.py
@@ -68,7 +68,7 @@ def get_long_description():
 
 setup(
     name=package_name,
-    version="3.0.0",
+    version="2.8.0.dev0",
     description="Python bindings for GPT4All",
     long_description=get_long_description(),
     long_description_content_type="text/markdown",