xtekky/gpt4free · error · ValueError

Model "{model_file}" not found.

Error message

Model "{model_file}" not found.

What it means

Thrown by LocalProvider.create_completion() when the cataloged model file is not present under the models directory and the interactive download prompt was declined (or received anything other than y/Y). Note it calls input(): in a non-TTY context (server, cron, subprocess) input() raises EOFError first, so this exact ValueError mostly appears in interactive sessions.

Source

Thrown at g4f/locals/provider.py:54

    def create_completion(
        model: str, messages: Messages, stream: bool = False, **kwargs
    ):
        global MODEL_LIST
        if MODEL_LIST is None:
            MODEL_LIST = get_models()
        if model not in MODEL_LIST:
            raise ValueError(f'Model "{model}" not found / not yet implemented')

        model = MODEL_LIST[model]
        model_file = model["path"]
        model_dir = find_model_dir(model_file)
        if not os.path.isfile(os.path.join(model_dir, model_file)):
            print(f'Model file "models/{model_file}" not found.')
            download = input(f"Do you want to download {model_file}? [y/n]: ")
            if download in ["y", "Y"]:
                GPT4All.download_model(model_file, model_dir)
            else:
                raise ValueError(f'Model "{model_file}" not found.')

        model = GPT4All(
            model_name=model_file,
            # n_threads=8,
            verbose=False,
            allow_download=False,
            model_path=model_dir,
        )

        system_message = "\n".join(
            message["content"] for message in messages if message["role"] == "system"
        )
        if system_message:
            system_message = "A chat between a curious user and an artificial intelligence assistant."

        prompt_template = "USER: {0}\nASSISTANT: "
        conversation = (
            "\n".join(

View on GitHub (pinned to 973504e177)

Solutions

1. Run once interactively and answer 'y' to let GPT4All.download_model fetch the file.
2. Or pre-download manually: place the GGUF from the catalog entry into the models dir with the exact 'path' filename from models.yaml.
3. For headless servers, pre-populate the models directory in the image/deploy step so the prompt never triggers (it also avoids the EOFError from input()).

Example fix

// before
# headless call with no model file on disk -> input() EOFError / decline -> ValueError
LocalProvider.create_completion(model=name, messages=msgs)

// after
# pre-provision the file (deploy step):
# curl -L -o models/<model_file_from_models_yaml> <gguf_url>
LocalProvider.create_completion(model=name, messages=msgs)

from g4f.locals.provider import get_models, find_model_dir
import os

def model_file_present(model: str) -> bool:
    entry = get_models().get(model)
    if entry is None:
        return False
    d = find_model_dir(entry["path"])
    return os.path.isfile(os.path.join(d, entry["path"]))

try:
    LocalProvider.create_completion(model=model, messages=msgs)
except (EOFError, ValueError) as e:
    # EOFError: input() in non-TTY; ValueError: download declined
    raise RuntimeError(f"model file missing for {model}; pre-provision it") from e

When it happens

Trigger: First use of a local model whose GGUF file was never downloaded; answering 'n' at the 'Do you want to download ...? [y/n]' prompt; a models dir where the file was deleted or the filename in models.yaml doesn't match what's on disk.

Common situations: Fresh installs expecting local models to be bundled (they are not); deployments where the prompt hangs or EOFs because stdin is closed; partial downloads leaving a wrong-sized/absent file.

Related errors

• Model "{model}" not found / not yet implemented
• Install "gpt4all" package | pip install -U g4f[local]

AI-assisted analysis of xtekky/gpt4free@973504e177 (2026-08-14). Data as JSON: /api/errors/5c7f005a5695b870. Report an issue: GitHub.