---
language:
- en
- zh
library_name: transformers
license: mit
base_model: zai-org/GLM-5.2-FP8
pipeline_tag: text-generation
tags:
- glm
- moe
- fp8
- pruned
- reap
- gaudi
---

# GLM-5.2-224E-FP8-REAP

This is an independently produced, expert-pruned derivative of
[`zai-org/GLM-5.2-FP8`](https://huggingface.co/zai-org/GLM-5.2-FP8). It is not
an official Z.ai release.

The checkpoint reduces each sparse MoE layer from 256 routed experts to 224
while preserving 8 active experts per token. Experts were selected with REAP
scores computed from actual router weights and unweighted expert-output norms.
The weights retain the source model's block-scaled FP8 format.

## Model Details

| Property | Value |
|---|---|
| Base model | `zai-org/GLM-5.2-FP8` |
| Architecture | `GlmMoeDsaForCausalLM` |
| Routed experts | 224 per sparse layer, reduced from 256 |
| Active experts | 8 per token |
| Hidden layers | 78 |
| Weight format | FP8, block size 128 x 128 |
| Weight shards | 141 Safetensors files |
| Weight payload | 663,759,907,008 bytes (618.17 GiB) |
| Source payload | 755,617,140,416 bytes |
| Payload reduction | 12.2% |
| License | MIT, inherited from the base model |

## Pruning Method

REAP calibration used 12,228 samples and 15,425,969 tokens across general,
code, reasoning, and agentic data. For every routed expert, the score was the
conditional mean of:

```text
actual_router_weight * L2(unweighted_expert_output)
```

The 32 lowest-scoring experts in each of the 75 sparse layers were removed.
The derivative was built directly from the immutable 256-expert source; it was
not produced by repeatedly pruning another derivative.

Keep-map SHA-256:
`6845c6d68d39934a5866b12b1222cd29da214b1080485cf39d8a9986b7c203f6`

## Validation

- Deep checkpoint validation: 104,037 of 104,037 tensors passed, with zero
  errors.
- Runtime functional checks: 4 of 4 passed, covering arithmetic, exact
  instruction following, long-context retrieval, and structured tool calling.
- Maximum context validated on the tested runtime: 131,072 tokens with BF16 KV
  cache.
- Aggregate context matrix passed at 16 x 8K, 8 x 16K, 4 x 32K, 2 x 64K, and
  1 x 126K.
- Sequential decode: 20.8689 output tokens/s on the tested 8-HPU setup.
- Concurrent decode: 263.5073 aggregate output tokens/s for 16 requests with
  128 output tokens each.

### Preliminary GPQA Check

A 10-question GPQA Diamond smoke sample scored 9/10 (90.0%) with no request
errors or malformed answers. The published base-model score is 91.2%, but this
small sample is not statistically sufficient for an exact quality comparison.
It used the OpenAI `simple-evals` zero-shot chain-of-thought prompt with
`temperature=1.0` and `top_p=0.95`.

## Deployment

The checkpoint was qualified with vLLM-Gaudi using tensor parallel 8, expert
parallel 8, BF16 KV cache, and MTP disabled. A representative configuration is:

```bash
vllm serve destr8803/GLM-5.2-224E-FP8-REAP \
  --tensor-parallel-size 8 \
  --enable-expert-parallel \
  --kv-cache-dtype auto \
  --max-model-len 131072
```

Hardware capacity, graph configuration, and supported context length depend on
the inference backend. The architecture advertises a larger nominal context,
but this derivative has only been runtime-qualified through 131,072 tokens.

GLM-5.2 uses thinking by default. Keep the default maximum reasoning effort for
benchmark reproduction; explicitly configure the serving framework if a lower
reasoning effort or disabled thinking is desired.

## Limitations

- This is a structural MoE pruning derivative. Removing experts can affect
  quality unevenly across domains even when aggregate smoke tests pass.
- The full official GLM-5.2 benchmark suite has not been reproduced.
- The preliminary 10-question GPQA result must not be interpreted as a complete
  benchmark result.
- Only the BF16 KV-cache runtime profile is quality-qualified. FP8 KV cache was
  not accepted for this release.
- Deployment requires substantial storage and accelerator memory.

The base model's intended-use, safety, and language limitations continue to
apply. Review the
[`zai-org/GLM-5.2`](https://huggingface.co/zai-org/GLM-5.2) model card before
deployment.

## License and Attribution

This derivative is distributed under the MIT license included in the
repository. GLM-5.2 was created by Z.ai and Tsinghua University. Please cite the
original technical report:

```bibtex
@misc{glm5team2026glm5vibecodingagentic,
  title={GLM-5: from Vibe Coding to Agentic Engineering},
  author={GLM-5-Team},
  year={2026},
  eprint={2602.15763},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2602.15763}
}
```