2noise/ChatTTS · error · ValueError

Quantization method specified in the model config ({hf_quant

Error message

Quantization method specified in the model config ({hf_quant_method}) does not match the quantization method specified in the `quantization` argument ({self.quantization}).

What it means

Error "Quantization method specified in the model config ({hf_quant_method}) does not match the quantization method specified in the `quantization` argument ({self.quantization})." thrown in 2noise/ChatTTS.

Source

Thrown at ChatTTS/model/velocity/configs.py:172

                f"Unknown tokenizer mode: {self.tokenizer_mode}. Must be "
                "either 'auto' or 'slow'."
            )
        self.tokenizer_mode = tokenizer_mode

    def _verify_quantization(self) -> None:
        supported_quantization = ["awq", "gptq", "squeezellm"]
        rocm_not_supported_quantization = ["awq"]
        if self.quantization is not None:
            self.quantization = self.quantization.lower()

        # Parse quantization method from the HF model config, if available.
        hf_quant_config = getattr(self.hf_config, "quantization_config", None)
        if hf_quant_config is not None:
            hf_quant_method = str(hf_quant_config["quant_method"]).lower()
            if self.quantization is None:
                self.quantization = hf_quant_method
            elif self.quantization != hf_quant_method:
                raise ValueError(
                    "Quantization method specified in the model config "
                    f"({hf_quant_method}) does not match the quantization "
                    f"method specified in the `quantization` argument "
                    f"({self.quantization})."
                )

        if self.quantization is not None:
            if self.quantization not in supported_quantization:
                raise ValueError(
                    f"Unknown quantization method: {self.quantization}. Must "
                    f"be one of {supported_quantization}."
                )
            if is_hip() and self.quantization in rocm_not_supported_quantization:
                raise ValueError(
                    f"{self.quantization} quantization is currently not supported "
                    f"in ROCm."
                )
            logger.warning(

View on GitHub (pinned to 77b89ee281)

When it happens

Trigger: Thrown at ChatTTS/model/velocity/configs.py:172 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of 2noise/ChatTTS@77b89ee281 (2026-08-26). Data as JSON: /api/errors/290792fe37dd8589. Report an issue: GitHub.