```CODE: 
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cerebras/GLM-4.6-REAP-218B-A32B-FP8")
model = AutoModelForCausalLM.from_pretrained("cerebras/GLM-4.6-REAP-218B-A32B-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))
```

ERROR: 
Traceback (most recent call last):
  File "/tmp/cerebras_GLM-4.6-REAP-218B-A32B-FP8_1iYzPml.py", line 20, in <module>
    model = AutoModelForCausalLM.from_pretrained("cerebras/GLM-4.6-REAP-218B-A32B-FP8")
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/models/auto/auto_factory.py", line 604, in from_pretrained
    return model_class.from_pretrained(
           ~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/modeling_utils.py", line 277, in _wrapper
    return func(*args, **kwargs)
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4881, in from_pretrained
    hf_quantizer, config, dtype, device_map = get_hf_quantizer(
                                              ~~~~~~~~~~~~~~~~^
        config, quantization_config, dtype, from_tf, from_flax, device_map, weights_only, user_agent
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 305, in get_hf_quantizer
    config.quantization_config = AutoHfQuantizer.merge_quantization_configs(
                                 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^
        config.quantization_config, quantization_config
        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    )
    ^
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 214, in merge_quantization_configs
    quantization_config = AutoQuantizationConfig.from_dict(quantization_config)
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/quantizers/auto.py", line 140, in from_dict
    return target_cls.from_dict(quantization_config_dict)
           ~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/utils/quantization_config.py", line 1398, in from_dict
    return super().from_dict(config_dict, return_unused_kwargs=return_unused_kwargs, **kwargs)
           ~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/utils/quantization_config.py", line 122, in from_dict
    config = cls(**config_dict)
  File "/tmp/.cache/uv/environments-v2/7eb248acb9b9547f/lib/python3.13/site-packages/transformers/utils/quantization_config.py", line 1328, in __init__
    raise ImportError(
        "compressed_tensors is not installed and is required for compressed-tensors quantization. Please install it with `pip install compressed-tensors`."
    )
ImportError: compressed_tensors is not installed and is required for compressed-tensors quantization. Please install it with `pip install compressed-tensors`.