GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
HawkBearPig
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
HawkBearPig
Model Tree
zai-org/GLM-5.3-BF16
Input Modalities
Output Modalities
Supported Functionality
Plain round-to-nearest with per-group min-max scales (llm-compressor's QuantizationModifier, no calibration
data, no activation-aware smoothing), one decoder layer at a time. Every layer is independent of every other, and
because nothing is folded into the norms there is no interaction with the router or the DSA indexer. This is the
simplest possible checkpoint in this format and the baseline the AWQ companion is measured against.
Relative RMS error against the bf16 layer on 32 × 2048 real tokens. "Contribution" is the error of what the layer adds (output minus input); "residual" is the error of the full residual stream leaving the layer, which is the quantity that propagates.
| layer | variant | contribution | residual |
|---|---|---|---|
| 3 | this checkpoint (RTN int4 g64) | 2.40 % | 0.54 % |
| 3 | AWQ int4 g64, fold-corrected (companion) | 2.38 % | 0.53 % |
| 3 | fp8 e4m3 g128 on every projection, for reference | 2.46 % | 0.55 % |
| 3 | int8 g64 on every projection, for reference | 1.49 % | 0.33 % |
| 6 (owns an indexer) | this checkpoint | 3.44 % | 1.58 % |
| 6 | AWQ, fold-corrected (companion) | 3.27 % | 1.50 % |
| 21 | this checkpoint | 11.09 % | 0.59 % |
| 21 | AWQ, fold-corrected (companion) | 10.95 % | 0.58 % |
The contribution metric grows with depth because each layer's addition shrinks relative to the residual stream;
the residual error stays at 0.5–1.5 %. On this model the int4/int8 mix lands at the error of an all-fp8 recipe at
half the bytes. The AWQ companion (HawkBearPig/GLM-5.3-Int4-Int8Mix-AWQ-g64) improves on this checkpoint by
1–5 % of the error depending on the layer (0.9 % at layer 3, 4.8 % at layer 6, 1.2 % at layer 21).
No end-to-end evaluation yet (perplexity, benchmarks): the numbers above are per-layer.
Standard compressed-tensors layout: model.safetensors.index.json, per-layer shards layer-NNN.safetensors,
passthrough.safetensors (embeddings, norms, lm_head, MTP block), config.json with quantization_config,
tokenizer files. Any loader that understands glm_moe_dsa and compressed-tensors pack-quantized W4A16/W8A16
should read it; only DGPP has been exercised. vLLM / transformers loading is untested.
Tooling: llm-compressor 0.13.0, compressed-tensors 0.18.0, transformers 5.14.1, torch 2.13.0, CPU-only build.
License: MIT, inherited from GLM-5.3.