LLM EXPLORER 60,062 MODELS INDEXED

GLM 5.3 Flash NVFP4 by tiyuvta

By tiyuvta · 248 downloads
HF Repo ↗ Copy URL

GLM 5.3 Flash NVFP4 is an open-source language model by tiyuvta. Features: 164.1b LLM, VRAM: 190.6GB, License: mit, LLM Explorer Score: 0.31.

  Arxiv:2602.15763   4-bit   8-bit Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3-fla...   Blackwell   Conversational   En   Fp4   Glm5 next   Memra   Modelopt   Moe   Nvfp4   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Tool-calling   W4a16   Zh
Model Card on HF 🤗: https://huggingface.co/tiyuvta/GLM-5.3-Flash-NVFP4 

GLM 5.3 Flash NVFP4 Parameters and Internals

LLM NameGLM 5.3 Flash NVFP4
Repository 🤗https://huggingface.co/tiyuvta/GLM-5.3-Flash-NVFP4 
Base Model(s)  zai-org/GLM-5.3-Flash   zai-org/GLM-5.3-Flash
Model Size164.1b
Required VRAM190.6 GB
Updated2026-08-31
Maintainertiyuvta
Model Typeglm5_next
Model Files  10.0 GB: 1-of-20   10.0 GB: 2-of-20   10.0 GB: 3-of-20   10.0 GB: 4-of-20   10.0 GB: 5-of-20   10.0 GB: 6-of-20   10.0 GB: 7-of-20   10.0 GB: 8-of-20   10.0 GB: 9-of-20   10.0 GB: 10-of-20   10.0 GB: 11-of-20   10.0 GB: 12-of-20   10.0 GB: 13-of-20   10.0 GB: 14-of-20   10.0 GB: 15-of-20   10.0 GB: 16-of-20   10.0 GB: 17-of-20   10.0 GB: 18-of-20   10.0 GB: 19-of-20   0.6 GB: 20-of-20
Supported Languagesen zh
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Model Max Length1048576
Transformers Version5.16.0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>