Skip to content

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

765 B
Raw Blame
from .config import parse_config
from .gguf import gguf_mm_config, iter_gguf_weights, parse_gguf_config, to_gguf
from .model import (
    Qwen3_5ForCausalLM,
    Qwen3_5ForConditionalGeneration,
    Qwen3_5MoeForCausalLM,
    Qwen3_5MoeForConditionalGeneration,
)
from .weight import iter_expert_pieces, iter_vision_weights, iter_weights, iter_weights_parallel, nvfp4_expert_spec

__all__ = [
    "Qwen3_5ForCausalLM",
    "Qwen3_5ForConditionalGeneration",
    "Qwen3_5MoeForCausalLM",
    "Qwen3_5MoeForConditionalGeneration",
    "parse_config",
    "iter_vision_weights",
    "iter_weights",
    "iter_weights_parallel",
    "iter_expert_pieces",
    "nvfp4_expert_spec",
    "gguf_mm_config",
    "iter_gguf_weights",
    "parse_gguf_config",
    "to_gguf",
]