What are the hardware requirements for GLM 4.5 Air FP8?

GLM 4.5 Air FP8 requires approximately 108.3 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM 4.5 Air FP8 and how large is it?

GLM 4.5 Air FP8 is developed by zai-org, a model with 110.5b 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 4.5 Air FP8?

GLM 4.5 Air FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 4.5 Air FP8 by zai-org — VRAM 108.3GB, 128K context

Name: GLM 4.5 Air FP8
Author: zai-org

GLM 4.5 Air FP8 is an open-source language model by zai-org. Features: 110.5b LLM, VRAM: 108.3GB, Context: 128K, License: mit, LLM Explorer Score: 0.28.

Arxiv:2508.06471 Agentic Code-generation Compressed-tensors Conversational Deploy:azure En Endpoints compatible Glm4 moe Reasoning Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/zai-org/GLM-4.5-Air-FP8

GLM 4.5 Air FP8 Parameters and Internals

LLM Name	GLM 4.5 Air FP8
Repository 🤗	https://huggingface.co/zai-org/GLM-4.5-Air-FP8
Model Size	110.5b
Required VRAM	108.3 GB
Updated	2026-08-08
Maintainer	zai-org
Model Type	glm4_moe
Model Files	2.7 GB: 1-of-47 2.4 GB: 2-of-47 2.4 GB: 3-of-47 2.4 GB: 4-of-47 2.4 GB: 5-of-47 2.4 GB: 6-of-47 2.4 GB: 7-of-47 2.4 GB: 8-of-47 2.4 GB: 9-of-47 2.4 GB: 10-of-47 2.4 GB: 11-of-47 2.4 GB: 12-of-47 2.4 GB: 13-of-47 2.4 GB: 14-of-47 2.4 GB: 15-of-47 2.4 GB: 16-of-47 2.4 GB: 17-of-47 2.4 GB: 18-of-47 2.4 GB: 19-of-47 2.4 GB: 20-of-47 2.4 GB: 21-of-47 2.4 GB: 22-of-47 2.4 GB: 23-of-47 2.4 GB: 24-of-47 2.4 GB: 25-of-47 2.4 GB: 26-of-47 2.4 GB: 27-of-47 2.4 GB: 28-of-47 2.4 GB: 29-of-47 2.4 GB: 30-of-47 2.4 GB: 31-of-47 2.4 GB: 32-of-47 2.4 GB: 33-of-47 2.4 GB: 34-of-47 2.4 GB: 35-of-47 2.4 GB: 36-of-47 2.4 GB: 37-of-47 2.4 GB: 38-of-47 2.4 GB: 39-of-47 2.4 GB: 40-of-47 2.4 GB: 41-of-47 2.4 GB: 42-of-47 2.4 GB: 43-of-47 2.4 GB: 44-of-47 2.4 GB: 45-of-47
Supported Languages	en zh
Model Architecture	Glm4MoeForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.54.0
Vocabulary Size	151552
Torch Data Type	bfloat16

Rank the GLM 4.5 Air FP8 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 4.5 Air FP8

Best Alternatives	Context / RAM	Downloads	Likes
GLM 4.5 Air	128K / 209.8 GB	474759	625
GLM 4.5 Air	128K / 209.8 GB	263343	8
GLM 4.5 Air Base	128K / 222.3 GB	594	46
GLM 4.5 Air Derestricted	128K / 209.8 GB	100	102
...5 Air Abliterated Lossytensors	128K / 221.7 GB	10	5

Note: green Score (e.g. "73.2") means that the model is better than zai-org/GLM-4.5-Air-FP8.