GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
destr8803
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
destr8803
Model Tree
zai-org/GLM-5.2-FP8
Input Modalities
Output Modalities
Supported Functionality
| 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 |
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
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.
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.
The base model's intended-use, safety, and language limitations continue to
apply. Review the
zai-org/GLM-5.2 model card before
deployment.
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}}