What are the hardware requirements for GLM 5.1 478B NVFP4?

GLM 5.1 478B NVFP4 requires approximately 154.9 GB of VRAM and supports a context window of 198K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM 5.1 478B NVFP4 and how large is it?

GLM 5.1 478B NVFP4 is developed by 0xSero, a model with 280.2b 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 5.1 478B NVFP4?

GLM 5.1 478B NVFP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 5.1 478B NVFP4 by 0xSero — VRAM 154.9GB, 198K context

Name: GLM 5.1 478B NVFP4
Author: 0xSero

GLM 5.1 478B NVFP4 is an open-source language model by 0xSero. Features: 280.2b LLM, VRAM: 154.9GB, Context: 198K, License: mit, MoE, LLM Explorer Score: 0.24.

Arxiv:2510.13999 8-bit Base model:quantized:zai-org/g... Base model:zai-org/glm-5.1 Blackwell Conversational Glm Glm moe dsa Modelopt Moe Nvfp4 Reap Region:us Safetensors Sglang Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/0xSero/GLM-5.1-478B-NVFP4

GLM 5.1 478B NVFP4 Parameters and Internals

LLM Name	GLM 5.1 478B NVFP4
Repository 🤗	https://huggingface.co/0xSero/GLM-5.1-478B-NVFP4
Base Model(s)	zai-org/GLM-5.1 zai-org/GLM-5.1
Model Size	280.2b
Required VRAM	154.9 GB
Updated	2026-09-03
Maintainer	0xSero
Model Type	glm_moe_dsa
Model Files	4.4 GB: 1-of-84 3.5 GB: 2-of-84 3.5 GB: 3-of-84 3.5 GB: 4-of-84 3.5 GB: 5-of-84 3.5 GB: 6-of-84 3.4 GB: 7-of-84 3.5 GB: 8-of-84 3.5 GB: 9-of-84 3.5 GB: 10-of-84 3.5 GB: 11-of-84 3.5 GB: 12-of-84 3.5 GB: 13-of-84 3.5 GB: 14-of-84 3.5 GB: 15-of-84 3.5 GB: 16-of-84 3.6 GB: 17-of-84 3.5 GB: 18-of-84 3.4 GB: 19-of-84 3.5 GB: 20-of-84 3.5 GB: 21-of-84 3.5 GB: 22-of-84 3.5 GB: 23-of-84 3.5 GB: 24-of-84 3.5 GB: 25-of-84 3.5 GB: 26-of-84 3.5 GB: 27-of-84 3.5 GB: 28-of-84 3.5 GB: 29-of-84 3.6 GB: 30-of-84 3.4 GB: 31-of-84 3.5 GB: 32-of-84 3.5 GB: 33-of-84 3.5 GB: 34-of-84 3.5 GB: 35-of-84 3.5 GB: 36-of-84 3.6 GB: 37-of-84 3.5 GB: 38-of-84 3.5 GB: 39-of-84 3.5 GB: 40-of-84 3.5 GB: 41-of-84 3.6 GB: 42-of-84 3.4 GB: 43-of-84 3.5 GB: 44-of-84
Model Architecture	GlmMoeDsaForCausalLM
License	mit
Context Length	202752
Model Max Length	202752
Transformers Version	5.4.0
Vocabulary Size	154880

Rank the GLM 5.1 478B 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 5.1 478B NVFP4

Best Alternatives	Context / RAM	Downloads	Likes
GLM 5.1 478B A42B REAP NVFP4	198K / 154.9 GB	3869	10

Note: green Score (e.g. "73.2") means that the model is better than 0xSero/GLM-5.1-478B-NVFP4.