gemma-4-31b-bf16 not working with oMLX 0.3.2

[liuxp2003]

Describe the bug
After loaded the model gemma-4-31b-bf16(mlx)

I got error response after sent message in chat page.
Error: {"error":{"message":"Chat template error: Cannot use chat template functions because tokenizer.chat_template is not set and no template argument was passed! For information about writing templates and setting the tokenizer.chat_template attribute, please see the documentation at https://huggingface.co/docs/transformers/main/en/chat_templating","type":"invalid_request_error","param":null,"code":null}}

To Reproduce
Steps to reproduce the behavior:

1. Download the mlx-community/gemma-4-31b-bf16 model from HF
2. Loaded the model
3. Open the chat page and input message.
4. See error

Expected behavior
I can get message response without error.

Screenshots
If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

• OS: macOS
• Browser: Chrome(146.0.7680.165)
• Version 26.4

Additional context
Add any other context about the problem here.

[RepublicOfKorokke]

I was having same issue, but I found the solution in #553

In short, you should use -it model.
such as: https://huggingface.co/mlx-community/gemma-4-31b-it-bf16/

[jundot]

This should be resolved in the latest release, which includes major improvements to Gemma 4 and TurboQuant support.

If you're still seeing issues after updating, please reopen this or file a new issue with updated logs.