➜  agent git:(agent) ✗ python3
Python 3.10.16 (main, Mar  4 2025, 12:34:35) [Clang 16.0.0 (clang-1600.0.26.6)] on darwin
Type "help", "copyright", "credits" or "license" for more information.
>>> from smolagents import MLXModel
Python-dotenv could not parse statement starting at line 33
>>> engine = MLXModel(model_id="mlx-community/gemma-3-4b-it-8bit",max_tokens=10000)
Fetching 10 files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 169125.16it/s]
ERROR:root:Model type gemma3 not supported.
Traceback (most recent call last):
  File "/Users/litan/.pyenv/versions/3.10.16/envs/shoppingwise/lib/python3.10/site-packages/mlx_lm/utils.py", line 148, in _get_classes
    arch = importlib.import_module(f"mlx_lm.models.{model_type}")
  File "/Users/litan/.pyenv/versions/3.10.16/lib/python3.10/importlib/__init__.py", line 126, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
  File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
  File "<frozen importlib._bootstrap>", line 1004, in _find_and_load_unlocked
ModuleNotFoundError: No module named 'mlx_lm.models.gemma3'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/Users/litan/.pyenv/versions/3.10.16/envs/shoppingwise/lib/python3.10/site-packages/smolagents/models.py", line 522, in __init__
    self.model, self.tokenizer = mlx_lm.load(model_id, tokenizer_config={"trust_remote_code": trust_remote_code})
  File "/Users/litan/.pyenv/versions/3.10.16/envs/shoppingwise/lib/python3.10/site-packages/mlx_lm/utils.py", line 785, in load
    model, config = load_model(model_path, lazy)
  File "/Users/litan/.pyenv/versions/3.10.16/envs/shoppingwise/lib/python3.10/site-packages/mlx_lm/utils.py", line 720, in load_model
    model_class, model_args_class = get_model_classes(config=config)
  File "/Users/litan/.pyenv/versions/3.10.16/envs/shoppingwise/lib/python3.10/site-packages/mlx_lm/utils.py", line 152, in _get_classes
    raise ValueError(msg)
ValueError: Model type gemma3 not supported.
>>> engine = MLXModel(model_id="mlx-community/gemma-3-4b-it-8bit",max_tokens=10000)

agent git:(agent) ✗ pip freeze | grep smolagents
openinference-instrumentation-smolagents==0.1.6
smolagents==1.10