---
title: GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound
canonical_url: "https://www.modelscope.ai/models/Intel/GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound"
md_url: "https://www.modelscope.ai/models/Intel/GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound.md"
repository: Intel/GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound
last_updated: 2026-10-27
license: mit
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - glm5_next
architectures:
  - Glm5NextForConditionalGeneration
base_model:
  - zai-org/GLM-5.3-Flash
base_model_relation: quantized
parameters: 175.3B
tensor_type:
  - U8
  - BF16
  - F32
  - F8_E4M3
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 21
stars: 0
---

# GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound

> GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound - An open-source model by Intel on ModelScope. This model is an MXFP4 model of GLM-5.3-Flash generated by intel/auto-round with RTN mode. Please follow the license of the original model.

Intel/GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound is a 175.3B-parameter text-generation model on ModelScope. licensed under mit. derived from zai-org/GLM-5.3-Flash.

- **Repository**: Intel/GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound
- **License**: mit
- **Tasks**: text-generation
- **Parameters**: 175.3B
- **Base model**: zai-org/GLM-5.3-Flash
- **Downloads**: 21
- **Stars**: 0
- **Last updated**: 2026-10-27

Source: https://www.modelscope.ai/models/Intel/GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound

---

This model is an MXFP4 model of [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash) generated by [intel/auto-round](https://github.com/intel/auto-round) with RTN mode. Please follow the license of the original model.

| Configuration | GSM8K | MMLU | PIQA | HelleSwag | Average | Relative to BF16 |
|--------------|-------|----------|----------|----------|----------|------------------|
| BF16 | 0.9735 | 0.8666 | 0.8292 | 0.6903| 0.8399 | - |
| MXFP4| 0.9735 | 0.8581 | 0.8313| 0.6836| 0.8366 | 99.61% |



## Generate the Model

~~~bash
auto-round \
  --model_name zai-org/GLM-5.3-Flash-BF16 \
  --model_free \
  --scheme MXFP8 \
  --ignore_layers "lm_head,embed_tokens,visual,hc_,indexer,self_attn,mlp.gate.,eh_proj,enorm,hnorm,shared_head,norm,A_log,dt_bias,b_proj,f_a_proj,f_b_proj,g_a_proj,g_b_proj,conv1d" \
   --layer_config "{mlp.experts:{bits:4,data_type:mx_fp}}"  \
  --format llm_compressor \
  --output_dir ./GLM-5.3-Flash-MXFP4-Mixed-CT-AutoRound
~~~



## Ethical Considerations and Limitations

The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.

Therefore, before deploying any applications of the model, developers should perform safety testing.

## Caveats and Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.

Here are a couple of useful links to learn more about Intel's AI software:

- [Intel Neural Compressor](https://github.com/intel/neural-compressor)

## Disclaimer

The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.

## Cite

@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }

[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round)