Skip to content

FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.

368 B
Raw Blame
from .config import parse_config
from .gguf import iter_gguf_weights, parse_gguf_config, to_gguf
from .model import Qwen3MoeForCausalLM
from .weight import iter_weights, iter_weights_parallel

__all__ = [
    "Qwen3MoeForCausalLM",
    "parse_config",
    "iter_weights",
    "iter_weights_parallel",
    "iter_gguf_weights",
    "parse_gguf_config",
    "to_gguf",
]