This is an NVFP4 checkpoint derived from
zai-org/GLM-5.3
.
It is optimized for Blackwell inference with NVFP4 weights and activations while retaining higher
precision where needed for model quality.
Model Optimizations
This model uses NVFP4 FP4 (E2M1) weights and activations and two-level scaling. Layers outside of routed experts are left unquantized.
The checkpoint uses
LLM Compressor
's
compressed-tensors NVFP4 format.
The source model was compressed using an LLM-Compressor with experimental layerwise decompression/compression along with an NVFP4 scheme using
perfectblend
calibration samples.
Evaluation
This model was evaluated on GSM8K Platinum, IFEval, MATH-500, AIME 2025, and GPQA Diamond using
lighteval
. Evaluation was run on a vLLM server hosted on 4xB200.
Generation used temperature 1.0, the
glm45
reasoning parser, FP8 E4M3 KV cache, and the same
serving stack for the NVFP4 and local FP8 baseline. GSM8K, IFEval, MATH-500, and GPQA used three
seeds; AIME used eight seeds. Recovery is relative to the
base model
run in the same evaluation harness.
GLM-5.3-NVFP4 huggingface.co is an AI model on huggingface.co that provides GLM-5.3-NVFP4's model effect (), which can be used instantly with this RedHatAI GLM-5.3-NVFP4 model. huggingface.co supports a free trial of the GLM-5.3-NVFP4 model, and also provides paid use of the GLM-5.3-NVFP4. Support call GLM-5.3-NVFP4 model through api, including Node.js, Python, http.
GLM-5.3-NVFP4 huggingface.co is an online trial and call api platform, which integrates GLM-5.3-NVFP4's modeling effects, including api services, and provides a free online trial of GLM-5.3-NVFP4, you can try GLM-5.3-NVFP4 online for free by clicking the link below.
RedHatAI GLM-5.3-NVFP4 online free url in huggingface.co:
GLM-5.3-NVFP4 is an open source model from GitHub that offers a free installation service, and any user can find GLM-5.3-NVFP4 on GitHub to install. At the same time, huggingface.co provides the effect of GLM-5.3-NVFP4 install, users can directly use GLM-5.3-NVFP4 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.