Support of Qwen3 GGUF model

[Auth0rM0rgan]

Hi, I am getting the following error when I want to use the GGUF model with Qwen3
"ValueError: GGUF model with architecture qwen3 is not supported yet."

I have the latest transformers and gguf-0.17.0

self.tokenizer = AutoTokenizer.from_pretrained(model_name, gguf_file= "Qwen3-0.6B-Q2_K_L.gguf",use_fast=True)
        if self.tokenizer.pad_token is None:
            self.tokenizer.pad_token = "<pad>"
            self.tokenizer.add_special_tokens({"pad_token": "<pad>"})
        self.tokenizer.padding_side = "left"
        self.model = AutoModelForCausalLM.from_pretrained(
            model_name,
            gguf_file = "Qwen3-0.6B-Q2_K_L.gguf",
            pad_token_id=self.tokenizer.pad_token_id,
            trust_remote_code=True,
            torch_dtype=torch.bfloat16,
            device_map="auto",
        )

How can I use the gguf model of Qwen3 with transformers? Could you please add the support of it?

Thanks!

[Rocketknight1]

There is an open PR for this #38645

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.