GLM 5 NVFP4 by nvidia

 ยป  All LLMs  ยป  nvidia  ยป  GLM 5 NVFP4   URL Share it on

GLM 5 NVFP4 is an open-source language model by nvidia. Features: 435.2b LLM, VRAM: 71.3GB, Context: 198K, License: mit, MoE.

  8-bit Base model:finetune:zai-org/gl...   Base model:zai-org/glm-5   Conversational   Fp4   Glm-5   Glm moe dsa   Model optimizer   Modelopt   Moe   Nvidia   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/nvidia/GLM-5-NVFP4 
GLM 5 NVFP4 (nvidia/GLM-5-NVFP4)
๐ŸŒŸ Advertise your project ๐Ÿš€

GLM 5 NVFP4 Parameters and Internals

LLM NameGLM 5 NVFP4
Repository ๐Ÿค—https://huggingface.co/nvidia/GLM-5-NVFP4 
Base Model(s)  GLM 5   zai-org/GLM-5
Model Size435.2b
Required VRAM71.3 GB
Updated2026-03-27
Maintainernvidia
Model Typeglm_moe_dsa
Model Files  4.7 GB: 1-of-282   1.6 GB: 2-of-282   1.5 GB: 3-of-282   1.5 GB: 4-of-282   1.8 GB: 5-of-282   1.5 GB: 6-of-282   1.5 GB: 7-of-282   1.5 GB: 8-of-282   1.8 GB: 9-of-282   1.5 GB: 10-of-282   1.5 GB: 11-of-282   1.5 GB: 12-of-282   1.8 GB: 13-of-282   1.5 GB: 14-of-282   1.5 GB: 15-of-282   1.8 GB: 16-of-282   1.5 GB: 17-of-282   1.5 GB: 18-of-282   1.5 GB: 19-of-282   1.8 GB: 20-of-282   1.5 GB: 21-of-282   1.5 GB: 22-of-282   1.5 GB: 23-of-282   1.8 GB: 24-of-282   1.5 GB: 25-of-282   1.5 GB: 26-of-282   1.8 GB: 27-of-282   1.5 GB: 28-of-282   1.5 GB: 29-of-282   1.5 GB: 30-of-282   1.8 GB: 31-of-282   1.5 GB: 32-of-282   1.5 GB: 33-of-282   1.5 GB: 34-of-282   1.8 GB: 35-of-282   1.5 GB: 36-of-282   1.5 GB: 37-of-282   1.9 GB: 38-of-282   1.6 GB: 39-of-282   1.5 GB: 40-of-282   1.5 GB: 41-of-282   1.8 GB: 42-of-282   1.5 GB: 43-of-282
Model ArchitectureGlmMoeDsaForCausalLM
Licensemit
Context Length202752
Model Max Length202752
Transformers Version5.0.2.dev0
Vocabulary Size154880

Rank the GLM 5 NVFP4 Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 51648 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260327b