What are the hardware requirements for GLM 5.3 Flash NVFP4?

GLM 5.3 Flash NVFP4 requires approximately 137.3 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM 5.3 Flash NVFP4 and how large is it?

GLM 5.3 Flash NVFP4 is developed by tattrongvu, a model with 165.5b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate GLM 5.3 Flash NVFP4?

GLM 5.3 Flash NVFP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 5.3 Flash NVFP4 by tattrongvu — VRAM 137.3GB

Name: GLM 5.3 Flash NVFP4
Author: tattrongvu

GLM 5.3 Flash NVFP4 is an open-source language model by tattrongvu. Features: 165.5b LLM, VRAM: 137.3GB, License: mit, LLM Explorer Score: 0.3.

8-bit Base model:quantized:zai-org/g... Base model:zai-org/glm-5.3-fla... Conversational Fp4 Glm5 next Image-text-to-text Modelopt Nvfp4 Region:us Safetensors Sglang Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/tattrongvu/GLM-5.3-Flash-NVFP4

GLM 5.3 Flash NVFP4 Parameters and Internals

LLM Name	GLM 5.3 Flash NVFP4
Repository 🤗	https://huggingface.co/tattrongvu/GLM-5.3-Flash-NVFP4
Base Model(s)	zai-org/GLM-5.3-Flash zai-org/GLM-5.3-Flash
Model Size	165.5b
Required VRAM	137.3 GB
Updated	2026-09-02
Maintainer	tattrongvu
Model Type	glm5_next
Model Files	4.2 GB: 1-of-62 3.7 GB: 2-of-62 3.2 GB: 3-of-62 3.2 GB: 4-of-62 3.2 GB: 5-of-62 3.0 GB: 6-of-62 3.2 GB: 7-of-62 3.2 GB: 8-of-62 3.0 GB: 9-of-62 3.2 GB: 10-of-62 3.2 GB: 11-of-62 3.2 GB: 12-of-62 3.0 GB: 13-of-62 3.2 GB: 14-of-62 3.2 GB: 15-of-62 3.0 GB: 16-of-62 3.6 GB: 17-of-62 3.2 GB: 18-of-62 3.2 GB: 19-of-62 3.0 GB: 20-of-62 3.2 GB: 21-of-62 3.2 GB: 22-of-62 3.0 GB: 23-of-62 3.2 GB: 24-of-62 3.2 GB: 25-of-62 3.2 GB: 26-of-62 3.0 GB: 27-of-62 3.2 GB: 28-of-62 3.2 GB: 29-of-62 3.0 GB: 30-of-62 3.2 GB: 31-of-62 3.2 GB: 32-of-62 3.2 GB: 33-of-62 3.0 GB: 34-of-62 3.2 GB: 35-of-62 3.2 GB: 36-of-62 3.0 GB: 37-of-62 3.2 GB: 38-of-62 3.2 GB: 39-of-62 3.2 GB: 40-of-62 3.0 GB: 41-of-62 3.2 GB: 42-of-62 3.2 GB: 43-of-62
Model Architecture	Glm5NextForConditionalGeneration
License	mit
Transformers Version	5.16.0
Torch Data Type	bfloat16

Rank the GLM 5.3 Flash NVFP4 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to GLM 5.3 Flash NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
...W4A16 NVFP4 K32 Experts FP8 WO	0K / 83.2 GB	28	6
GLM 5.3 Flash NVFP4	0K / 73.1 GB	0	35
GLM 5.3 Flash UNCENSORED NVFP4	0K / 69.8 GB	3210	27

Note: green Score (e.g. "73.2") means that the model is better than tattrongvu/GLM-5.3-Flash-NVFP4.