RedHatAI / GLM-5.3-NVFP4

huggingface.co
Total runs: 4.0K
24-hour runs: 0
7-day runs: 0
30-day runs: 3.6K
Model's Last Updated: September 24 2026
text-generation

Introduction of GLM-5.3-NVFP4

Model Details of GLM-5.3-NVFP4

GLM-5.3-NVFP4

Model Overview
  • Model Architecture: GlmMoeDsaForCausalLM
    • Input: Text
    • Output: Text
  • Model Optimizations:
    • Weight quantization: NVFP4
    • Activation quantization: NVFP4
  • Format: compressed-tensors
  • Base model: zai-org/GLM-5.3

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.

Deployment
vLLM Serving
vllm serve RedHatAI/GLM-5.3-NVFP4 \
  --served-model-name GLM-5.3-NVFP4 \
  --tensor-parallel-size 4 \
  --kv-cache-dtype fp8_e4m3 \
  --reasoning-parser glm45 \
  --chat-template-content-format string \
  --max-model-len 69632 \
  --speculative-config '{"method":"mtp","num_speculative_tokens":5}' \
  --trust-remote-code
Creation

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.

Accuracy
Category Benchmark RedHatAI/GLM-5.3-NVFP4 zai-org/GLM-5.3 (FP8) Recovery
Instruction Following IFEval (prompt-level strict) 85.70% 89.77% 95.5%
Reasoning GSM8K Platinum (strict-match) 96.69% 97.52% 99.1%
MATH-500 (pass@1) 96.27% 95.07% 101.3%
AIME 2025 (pass@1) 89.58% 92.50% 96.8%
GPQA Diamond (pass@1) 90.40% 92.42% 97.8%

Per-seed NVFP4 results:

  • GSM8K: 96.36%, 96.86%, 96.86%
  • IFEval: 85.95%, 85.95%, 85.21%
  • MATH-500: 96.00%, 96.60%, 96.20%
  • AIME 2025: 90.00%, 86.67%, 90.00%, 90.00%, 93.33%, 90.00%, 86.67%, 90.00%
  • GPQA Diamond: 90.40%, 91.41%, 89.39%

Runs of RedHatAI GLM-5.3-NVFP4 on huggingface.co

4.0K
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
3.6K
30-day runs

More Information About GLM-5.3-NVFP4 huggingface.co Model

More GLM-5.3-NVFP4 license Visit here:

https://choosealicense.com/licenses/glm-5.3

GLM-5.3-NVFP4 huggingface.co

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 Url

https://huggingface.co/RedHatAI/GLM-5.3-NVFP4

RedHatAI GLM-5.3-NVFP4 online free

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:

https://huggingface.co/RedHatAI/GLM-5.3-NVFP4

GLM-5.3-NVFP4 install

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.

GLM-5.3-NVFP4 install url in huggingface.co:

https://huggingface.co/RedHatAI/GLM-5.3-NVFP4

Url of GLM-5.3-NVFP4

GLM-5.3-NVFP4 huggingface.co Url

Provider of GLM-5.3-NVFP4 huggingface.co

RedHatAI
ORGANIZATIONS

Other API from RedHatAI

huggingface.co

Total runs: 26.2K
Run Growth: -15.7K
Growth Rate: -59.90%
Updated:May 18 2026
huggingface.co

Total runs: 20.9K
Run Growth: -11.8K
Growth Rate: -56.48%
Updated:April 29 2026