GLM-4.7-Flash-Trellis-MM

GLM-4.7-Flash-Trellis-MM/
├── model-00001-of-00007.safetensors   # ~2 GB each
├── model-00002-of-00007.safetensors
├── model-00003-of-00007.safetensors
├── model-00004-of-00007.safetensors
├── model-00005-of-00007.safetensors
├── model-00006-of-00007.safetensors
├── model-00007-of-00007.safetensors
├── model.safetensors.index.json       # Weight map
├── base_weights.safetensors           # Embeddings, norms (FP16)
├── config.json                        # Model config
├── tokenizer.json                     # Tokenizer
├── tokenizer_config.json
└── quantization_index.json            # Quantization metadata

from metal_marlin.trellis import TrellisForCausalLM
from transformers import AutoTokenizer

model = TrellisForCausalLM.from_pretrained(
    "RESMP-DEV/GLM-4.7-Flash-Trellis-3.8bpw",
    device="mps"
)
tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-4.7-Flash")

prompt = "<|user|>\nExplain quantum computing in simple terms.\n<|assistant|>\n"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("mps")
output = model.generate(input_ids, max_new_tokens=256, temperature=0.7)
print(tokenizer.decode(output[0], skip_special_tokens=True))

@misc{glm2025glm45,
      title={GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models}, 
      author={GLM Team and Aohan Zeng and Xin Lv and others},
      year={2025},
      eprint={2508.06471},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.06471}, 
}