LLM EXPLORER 59,805 MODELS INDEXED

GLM 5.3 Flash NVFP4 by RedHatAI

By RedHatAI · 7206 downloads

GLM 5.3 Flash NVFP4 is an open-source language model by RedHatAI. Features: 169.1b LLM, VRAM: 190.2GB, LLM Explorer Score: 0.41.

  8-bit Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3-fla...   Compressed-tensors   Conversational   Endpoints compatible   Fp4   Glm5 next   Image-text-to-text   Llm-compressor   Nvfp4   Region:us   Safetensors   Sharded   Tensorflow   Vllm

GLM 5.3 Flash NVFP4 Parameters and Internals

LLM NameGLM 5.3 Flash NVFP4
Repository πŸ€—https://huggingface.co/RedHatAI/GLM-5.3-Flash-NVFP4 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size169.1b
Required VRAM190.2 GB
Updated2026-08-29
MaintainerRedHatAI
Model Typeglm5_next
Model Files  20.0 GB: 1-of-10   20.0 GB: 2-of-10   20.0 GB: 3-of-10   20.0 GB: 4-of-10   20.0 GB: 5-of-10   20.0 GB: 6-of-10   20.0 GB: 7-of-10   20.0 GB: 8-of-10   20.0 GB: 9-of-10   10.2 GB: 10-of-10   7.6 GB
Model ArchitectureGlm5NextForConditionalGeneration
Model Max Length1048576
Transformers Version5.16.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>