What are the hardware requirements for GLM 4.7?

GLM 4.7 requires approximately 327.5 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 4.7 and how large is it?

GLM 4.7 is developed by zai-org, a model with 358.3b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does GLM 4.7 perform on standard benchmarks?

GLM 4.7 has the following published scores: LMSYS ELO 1442. Compare against reference models on this page or on the LLM Explorer leaderboards.

GLM 4.7 by zai-org — VRAM 327.5GB, 198K context

Name: GLM 4.7
Author: zai-org

GLM 4.7 is an open-source language model by zai-org. Features: 358.3b LLM, VRAM: 327.5GB, Context: 198K, License: mit, LLM Explorer Score: 0.53, ELO: 1442.

Arxiv:2508.06471 Conversational Deploy:azure En Endpoints compatible Eval-results Glm4 moe Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/zai-org/GLM-4.7

GLM 4.7 Benchmarks

LMSys ELO 1442 vs 1272 (so35) 13.4%

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

GLM 4.7 Parameters and Internals

LLM Name	GLM 4.7
Repository 🤗	https://huggingface.co/zai-org/GLM-4.7
Model Size	358.3b
Required VRAM	327.5 GB
Updated	2026-07-25
Maintainer	zai-org
Model Type	glm4_moe
Model Files	2.2 GB: 1-of-92 0.7 GB: 2-of-92 0.7 GB: 3-of-92 7.9 GB: 4-of-92 7.9 GB: 5-of-92 7.9 GB: 6-of-92 7.9 GB: 7-of-92 7.9 GB: 8-of-92 7.9 GB: 9-of-92 7.9 GB: 10-of-92 7.9 GB: 11-of-92 7.9 GB: 12-of-92 7.9 GB: 13-of-92 7.9 GB: 14-of-92 7.9 GB: 15-of-92 7.9 GB: 16-of-92 7.9 GB: 17-of-92 7.9 GB: 18-of-92 7.9 GB: 19-of-92 7.9 GB: 20-of-92 7.9 GB: 21-of-92 7.9 GB: 22-of-92 7.9 GB: 23-of-92 7.9 GB: 24-of-92 7.9 GB: 25-of-92 7.9 GB: 26-of-92 7.9 GB: 27-of-92 7.9 GB: 28-of-92 7.9 GB: 29-of-92 7.9 GB: 30-of-92 7.9 GB: 31-of-92 7.9 GB: 32-of-92 7.9 GB: 33-of-92 7.9 GB: 34-of-92 7.9 GB: 35-of-92 7.9 GB: 36-of-92 7.9 GB: 37-of-92 7.9 GB: 38-of-92 7.9 GB: 39-of-92 7.9 GB: 40-of-92 7.9 GB: 41-of-92 7.9 GB: 42-of-92 7.9 GB: 43-of-92 7.9 GB: 44-of-92
Supported Languages	en zh
Model Architecture	Glm4MoeForCausalLM
License	mit
Context Length	202752
Model Max Length	202752
Transformers Version	4.54.0
Vocabulary Size	151552
Torch Data Type	bfloat16

Rank the GLM 4.7 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 4.7

Model	Likes	Downloads	VRAM
GLM 4.7 4bit	5	2822	197 GB
GLM 4.7 8bit Gs32	4	1937	198 GB
GLM 4.7 8bit	3	144	189 GB

Best Alternatives to GLM 4.7

Best Alternatives	Context / RAM	Downloads	Likes
GLM 4.7	198K / 335.4 GB	18	10
GLM 4.5	128K / 337 GB	160781	1403
GLM 4.5	128K / 337 GB	17	7
GLM 4.5 Base	128K / 250.7 GB	999	61