---
base_model:
- zai-org/GLM-4.7-Flash
license: mit
pipeline_tag: text-generation
library_name: transformers
tags:
- glm
---

> [!TIP]
> **[Support this work →](https://donate.sybilsolutions.ai)** · [X](https://x.com/0xsero) · [GitHub](https://github.com/0xsero) · [REAP paper](https://arxiv.org/abs/2510.13999) · [Cerebras REAP](https://huggingface.co/collections/cerebras/cerebras-reap)

# GLM-4.7-Flash

REAP-pruned [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash).

## At a glance

| | |
|---|---|
| Base model | [zai-org/GLM-4.7-Flash](https://huggingface.co/zai-org/GLM-4.7-Flash) |
| Format | BF16 |
| Total params | **30B** |
| Active / token | — |
| Experts / layer | 64 |
| Layers | 47 |
| Hidden size | 2048 |
| Context | 202,752 |
| On-disk size | 120 GB |

## Which variant should I pick?

| Variant | Format | Link |
|---|---|---|
| `GLM-4.7-Flash` **(this)** | BF16 | [link](https://huggingface.co/0xSero/GLM-4.7-Flash) |
| `GLM-4.7-Flash-DPO` | DPO | [link](https://huggingface.co/0xSero/GLM-4.7-Flash-DPO) |
| `GLM-4.7-Flash-SFT` | SFT | [link](https://huggingface.co/0xSero/GLM-4.7-Flash-SFT) |
| `GLM-4.7-Flash-Tools` | Tools | [link](https://huggingface.co/0xSero/GLM-4.7-Flash-Tools) |

## License & citation
License inherited from the base model.

```bibtex
@misc{lasby2025reap,
  title  = {REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author = {Mike Lasby and Ivan Lazarevich and Nish Sinnadurai and Sean Lie and Yani Ioannou and Vithursan Thangarasa},
  year   = {2025}, eprint = {2510.13999}, archivePrefix = {arXiv}
}
```

## Sponsors
Made possible by **NVIDIA · TNG Technology · Lambda · Prime Intellect · Hot Aisle**.