What are the hardware requirements for GLM 5.3 BF16?

GLM 5.3 BF16 requires approximately 237.4 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 5.3 BF16 and how large is it?

GLM 5.3 BF16 is developed by zai-org, 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 5.3 BF16?

GLM 5.3 BF16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 5.3 BF16 by zai-org — VRAM 237.4GB, 1024K context

Name: GLM 5.3 BF16
Author: zai-org

GLM 5.3 BF16 is an open-source language model by zai-org. Features: 753.3b LLM, VRAM: 237.4GB, Context: 1024K, License: other, MoE, LLM Explorer Score: 0.29.

Arxiv:2602.15763 Conversational En Endpoints compatible Glm moe dsa Moe Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/zai-org/GLM-5.3-BF16

GLM 5.3 BF16 Parameters and Internals

LLM Name	GLM 5.3 BF16
Repository 🤗	https://huggingface.co/zai-org/GLM-5.3-BF16
Model Size	753.3b
Required VRAM	237.4 GB
Updated	2026-08-29
Maintainer	zai-org
Model Type	glm_moe_dsa
Model Files	5.3 GB: 1-of-282 5.3 GB: 2-of-282 5.4 GB: 3-of-282 5.4 GB: 4-of-282 5.4 GB: 5-of-282 5.4 GB: 6-of-282 5.4 GB: 7-of-282 5.4 GB: 8-of-282 5.4 GB: 9-of-282 5.4 GB: 10-of-282 5.4 GB: 11-of-282 5.4 GB: 12-of-282 5.4 GB: 13-of-282 5.4 GB: 14-of-282 5.4 GB: 15-of-282 5.4 GB: 16-of-282 5.4 GB: 17-of-282 5.4 GB: 18-of-282 5.4 GB: 19-of-282 5.4 GB: 20-of-282 5.4 GB: 21-of-282 5.4 GB: 22-of-282 5.4 GB: 23-of-282 5.4 GB: 24-of-282 5.4 GB: 25-of-282 5.4 GB: 26-of-282 5.4 GB: 27-of-282 5.4 GB: 28-of-282 5.4 GB: 29-of-282 5.4 GB: 30-of-282 5.4 GB: 31-of-282 5.4 GB: 32-of-282 5.4 GB: 33-of-282 5.4 GB: 34-of-282 5.4 GB: 35-of-282 5.4 GB: 36-of-282 5.4 GB: 37-of-282 5.4 GB: 38-of-282 5.4 GB: 39-of-282 5.4 GB: 40-of-282 5.4 GB: 41-of-282 5.4 GB: 42-of-282 5.4 GB: 43-of-282 5.4 GB: 44-of-282
Supported Languages	en zh
Model Architecture	GlmMoeDsaForCausalLM
License	other
Context Length	1048576
Model Max Length	1048576
Transformers Version	5.15.0
Vocabulary Size	154880

Rank the GLM 5.3 BF16 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

Quantized Models of the GLM 5.3 BF16

Model	Likes	Downloads	VRAM
... 5.3 Mixed346 GPTQ H32 A8 G128	2	262	0 GB
GLM 5.3 4bit	1	1229	207 GB
GLM 5.3 Mixed 4 5bit	1	532	181 GB

Best Alternatives to GLM 5.3 BF16

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 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
GLM 5.2	1024K / 237.4 GB	1671	26

Note: green Score (e.g. "73.2") means that the model is better than zai-org/GLM-5.3-BF16.