LLM EXPLORER 67,952 MODELS INDEXED

GLM 5.3 Flash NVFP4 REAP25 by inference-optimization

By inference-optimization · 41 downloads

GLM 5.3 Flash NVFP4 REAP25 is an open-source language model by inference-optimization. Features: 131.1b LLM, VRAM: 147.4GB, License: mit, LLM Explorer Score: 0.3.

  8-bit Base model:quantized:redhatai/... Base model:redhatai/glm-5.3-fl...   Compressed-tensors   Conversational   En   Endpoints compatible   Expert-pruning   Fp4   Glm5 next   Image-text-to-text   Llm-compressor   Nvfp4   Reap   Region:us   Safetensors   Sharded   Tensorflow   Vllm   Zh

GLM 5.3 Flash NVFP4 REAP25 Parameters and Internals

LLM NameGLM 5.3 Flash NVFP4 REAP25
Repository πŸ€—https://huggingface.co/inference-optimization/GLM-5.3-Flash-NVFP4-REAP25 
Base Model(s)  RedHatAI/GLM-5.3-Flash-NVFP4   RedHatAI/GLM-5.3-Flash-NVFP4
Model Size131.1b
Required VRAM147.4 GB
Updated2026-11-19
Maintainerinference-optimization
Model Typeglm5_next
Model Files  16.3 GB: 1-of-10   15.5 GB: 2-of-10   15.3 GB: 3-of-10   15.4 GB: 4-of-10   15.3 GB: 5-of-10   15.4 GB: 6-of-10   15.3 GB: 7-of-10   15.4 GB: 8-of-10   15.4 GB: 9-of-10   8.1 GB: 10-of-10   7.6 GB
Supported Languagesen zh
Model ArchitectureGlm5NextForConditionalGeneration
Licensemit
Model Max Length1048576
Transformers Version5.16.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>