LLM EXPLORER 60,897 MODELS INDEXED

GLM 5.3 Flash NVFP4 by nvidia

By nvidia · 3391 downloads
HF Repo ↗ Copy URL

GLM 5.3 Flash NVFP4 is an open-source language model by nvidia. Features: 168.9b LLM, VRAM: 203.9GB, License: mit, LLM Explorer Score: 0.4.

  8-bit Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3-fla...   Conversational   Fp4   Glm-5   Glm5 next   Image-text-to-text   Model optimizer   Modelopt   Nvidia   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nvidia/GLM-5.3-Flash-NVFP4 

GLM 5.3 Flash NVFP4 Parameters and Internals

LLM NameGLM 5.3 Flash NVFP4
Repository 🤗https://huggingface.co/nvidia/GLM-5.3-Flash-NVFP4 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size168.9b
Required VRAM203.9 GB
Updated2026-09-11
Maintainernvidia
Model Typeglm5_next
Model Files  8.9 GB: 1-of-33   8.9 GB: 2-of-33   8.9 GB: 3-of-33   6.0 GB: 4-of-33   6.0 GB: 5-of-33   5.9 GB: 6-of-33   5.9 GB: 7-of-33   5.9 GB: 8-of-33   5.9 GB: 9-of-33   5.9 GB: 10-of-33   5.9 GB: 11-of-33   5.9 GB: 12-of-33   5.9 GB: 13-of-33   5.9 GB: 14-of-33   5.9 GB: 15-of-33   5.9 GB: 16-of-33   5.9 GB: 17-of-33   5.9 GB: 18-of-33   5.9 GB: 19-of-33   5.9 GB: 20-of-33   5.9 GB: 21-of-33   5.9 GB: 22-of-33   5.9 GB: 23-of-33   5.9 GB: 24-of-33   5.9 GB: 25-of-33   5.9 GB: 26-of-33   5.9 GB: 27-of-33   5.9 GB: 28-of-33   5.9 GB: 29-of-33   5.9 GB: 30-of-33   5.9 GB: 31-of-33   5.9 GB: 32-of-33   5.9 GB: 33-of-33
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Model Max Length1048576
Transformers Version5.16.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>