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-5.3
Input Modalities
Output Modalities
Supported Functionality
Experts were selected with Mean Activation Norm (MAN):
text
S(1,0,1) = mean(l2(unweighted_expert_output)) over tokens routed to the expert
For each sparse layer, the 224 experts with the largest MAN scores are retained.
No retraining, fine-tuning, merging, or weight averaging is applied. Seven
activation-outlier candidates in layer 77 were protected with the conservative
guardrail max_abs > max(global_p99.5, global_max / 10). The MTP layer reuses
the layer-77 keep IDs.
This reduces the routed-expert count by 12.5%, from 256 to 224, while preserving top-8 routing.
The deterministic calibration subset contains 2,848 samples and 1,983,722 tokens, with approximately 500,000 tokens per axis:
| Axis | Samples | Tokens |
|---|---|---|
| General | 1,128 | 495,244 |
| Code | 912 | 500,387 |
| Agentic | 648 | 497,302 |
| Reasoning | 160 | 490,789 |
The source pool used public data from:
allenai/c4 (en)theblackcat102/evol-codealpaca-v1open-r1/Mixture-of-Thoughts (code, math, and science)glaiveai/glaive-function-calling-v2SWE-bench/SWE-smith-trajectories (tool)The calibration data is not included in this model repository. The subset was
selected with seed 42, without packing or truncation, and scored across eight
Gaudi2 ranks. Its SHA-256 is
27bdf438f05019d65655c2f0db7ef0b7f994d3c2b250abe66244f30af986a372.
The materialized checkpoint passed deep structural and tensor validation:
| Check | Result |
|---|---|
| Safetensors shards | 141 |
| Indexed tensors checked | 104,037 / 104,037 |
| Indexed tensor payload | 663,759,907,008 bytes |
| Routed experts per sparse layer | 224 |
| Functional runtime checks | 4 / 4 |
| Behavior checks across low/high/max reasoning effort | 12 / 12 |
| GPQA Diamond deterministic 40-question subset | 39 / 40 (97.5%) |
The GPQA run used the public OpenAI simple-evals GPQA Diamond CSV with one
deterministic permutation per question, seed 0, temperature=1.0, top_p=0.95,
and a maximum output of 120,000 tokens in a 131,072-token context. The clustered
bootstrap 95% interval was 92.5%-100%. This is a 40-question evaluation, not a
claim of performance on the complete benchmark or under the unpublished Z.ai
evaluation protocol.
The checkpoint was runtime-qualified with vLLM on eight Intel Gaudi2 devices using tensor parallelism 8, expert parallelism 8, BF16 KV cache, and a 131,072-token maximum context. In that environment it produced 19.72 tokens/s single-stream and 237.03 aggregate tokens/s across 16 concurrent 1,024-token generations. These throughput figures are hardware- and configuration-specific.
See prune-report.json for hashes and machine-readable
provenance.
Use a recent Transformers or vLLM release with GLM-5.3, FP8 MoE, and the target
accelerator supported. Follow the upstream
zai-org/GLM-5.3 chat-template and
serving guidance. In particular, GLM-5.3 supports reasoning_effort values
low, high, and max; benchmark validation used the default max behavior.
Deployment has been validated on Gaudi2 with TP8/EP8. CUDA and other backends were not qualified as part of this release.
LICENSE before use.For the base model architecture, capabilities, citation, and intended use, see
the upstream zai-org/GLM-5.3 model
card.