GLM-4.7-REAP-50-W4A16

GLM-4.7 (358B, 700GB)
        │
        ▼  REAP 50% expert pruning
        │
GLM-4.7-REAP-50 (179B)
        │
        ▼  AutoRound W4A16 quantization
        │
GLM-4.7-REAP-50-W4A16 (~92GB)  ◀── This model

Total: ~6.5x compression

vllm serve 0xSero/GLM-4.7-REAP-50-W4A16 \
    --tensor-parallel-size 4 \
    --trust-remote-code \
    --quantization gptq

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "0xSero/GLM-4.7-REAP-50-W4A16",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("0xSero/GLM-4.7-REAP-50-W4A16", trust_remote_code=True)

#!/usr/bin/env python3
"""
AutoRound W4A16 Quantization
Intel's state-of-the-art weight quantization using signed gradient descent.
"""

from auto_round import AutoRound

def quantize_w4a16(
    model_path: str,
    output_dir: str,
    bits: int = 4,
    group_size: int = 128,
    format: str = "auto_gptq",
):
    """
    Quantize model to INT4 weights with FP16 activations.

    Args:
        model_path: Path to REAP-pruned model
        output_dir: Output directory
        bits: Weight bit width (4 for W4A16)
        group_size: Quantization group size (128 is optimal)
        format: Output format (auto_gptq for vLLM compatibility)
    """
    ar = AutoRound(
        model_path,
        scheme="W4A16",
        device="cuda",
        device_map="auto",
        trust_remote_code=True,
        batch_size=1,
        seqlen=512,
        nsamples=64,
    )
    ar.quantize_and_save(output_dir, format=format)

# Example: Quantize REAP-40 to W4A16
quantize_w4a16(
    model_path="./GLM-4.7-REAP-40",
    output_dir="./GLM-4.7-REAP-40-W4A16",
)

@article{lasby2025reap,
  title={REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author={Lasby, Mike and Lazarevich, Ivan and Sinnadurai, Nish and Lie, Sean and Ioannou, Yani and Thangarasa, Vithursan},
  journal={arXiv preprint arXiv:2510.13999},
  year={2025},
  url={https://arxiv.org/abs/2510.13999}
}