What are the hardware requirements for GLM 5.2 MXFP4xMXFP8?

GLM 5.2 MXFP4xMXFP8 requires approximately 68.1 GB of VRAM and supports a context window of 1024K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM 5.2 MXFP4xMXFP8 and how large is it?

GLM 5.2 MXFP4xMXFP8 is developed by RedHatAI, a model with 753.3b 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 5.2 MXFP4xMXFP8?

GLM 5.2 MXFP4xMXFP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 5.2 MXFP4xMXFP8 by RedHatAI — VRAM 68.1GB, 1024K context

Name: GLM 5.2 MXFP4xMXFP8
Author: RedHatAI

GLM 5.2 MXFP4xMXFP8 is an open-source language model by RedHatAI. Features: 753.3b LLM, VRAM: 68.1GB, Context: 1024K, License: mit, MoE, LLM Explorer Score: 0.27.

Arxiv:2602.15763 Arxiv:2603.12201 8-bit Compressed-tensors Conversational En Endpoints compatible Eval-results Glm moe dsa Moe Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/RedHatAI/GLM-5.2-MXFP4xMXFP8

GLM 5.2 MXFP4xMXFP8 Parameters and Internals

LLM Name	GLM 5.2 MXFP4xMXFP8
Repository 🤗	https://huggingface.co/RedHatAI/GLM-5.2-MXFP4xMXFP8
Model Size	753.3b
Required VRAM	68.1 GB
Updated	2026-08-20
Maintainer	RedHatAI
Model Type	glm_moe_dsa
Model Files	5.3 GB: 1-of-282 1.5 GB: 2-of-282 1.4 GB: 3-of-282 1.4 GB: 4-of-282 1.7 GB: 5-of-282 1.4 GB: 6-of-282 1.4 GB: 7-of-282 1.4 GB: 8-of-282 1.7 GB: 9-of-282 1.4 GB: 10-of-282 1.4 GB: 11-of-282 1.4 GB: 12-of-282 1.7 GB: 13-of-282 1.4 GB: 14-of-282 1.4 GB: 15-of-282 1.7 GB: 16-of-282 1.4 GB: 17-of-282 1.4 GB: 18-of-282 1.4 GB: 19-of-282 1.7 GB: 20-of-282 1.4 GB: 21-of-282 1.4 GB: 22-of-282 1.4 GB: 23-of-282 1.7 GB: 24-of-282 1.4 GB: 25-of-282 1.4 GB: 26-of-282 1.7 GB: 27-of-282 1.4 GB: 28-of-282 1.4 GB: 29-of-282 1.4 GB: 30-of-282 1.7 GB: 31-of-282 1.4 GB: 32-of-282 1.4 GB: 33-of-282 1.4 GB: 34-of-282 1.7 GB: 35-of-282 1.4 GB: 36-of-282 1.4 GB: 37-of-282 2.3 GB: 38-of-282 1.4 GB: 39-of-282 1.4 GB: 40-of-282 1.4 GB: 41-of-282 1.7 GB: 42-of-282 1.4 GB: 43-of-282
Supported Languages	en zh
Model Architecture	GlmMoeDsaForCausalLM
License	mit
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.12.0
Vocabulary Size	154880

Rank the GLM 5.2 MXFP4xMXFP8 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 5.2 MXFP4xMXFP8

Best Alternatives	Context / RAM	Downloads	Likes
GLM 5.3	1024K / 232.2 GB	8804	1255
GLM 5.2	1024K / 232 GB	2391730	4875
Atria Dawn Preview	1024K / 183.2 GB	1688	248
...3 F.U AnthraClaud Edition BF16	1024K / 428 GB	1259	60
GLM 5.3 NVFP4	1024K / 465.2 GB	1973	3
GLM 5.3 BF16	1024K / 237.4 GB	482	24
GLM 5.3 DERISKED BF16	1024K / 428 GB	67	60
GLM 5.3 CYBERSECURITY FP8	1024K / 112.6 GB	227	29
Macaron V1.1	1024K / 221.2 GB	202	8
GLM 5.3 MXFP4	1024K / 132.2 GB	649	1

Note: green Score (e.g. "73.2") means that the model is better than RedHatAI/GLM-5.2-MXFP4xMXFP8.