What are the hardware requirements for GLM 4.6 5bit?

GLM 4.6 5bit requires approximately 228.6 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 4.6 5bit and how large is it?

GLM 4.6 5bit is developed by mlx-community, a model with 352.8b 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 4.6 5bit?

GLM 4.6 5bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 4.6 5bit by mlx-community — VRAM 228.6GB, 198K context

Name: GLM 4.6 5bit
Author: mlx-community

GLM 4.6 5bit is an open-source language model by mlx-community. Features: 352.8b LLM, VRAM: 228.6GB, Context: 198K, License: mit, Quantized, LLM Explorer Score: 0.2.

5-bit 5bit Base model:quantized:zai-org/g... Base model:zai-org/glm-4.6 Conversational En Glm4 moe Mlx Quantized Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/GLM-4.6-5bit

GLM 4.6 5bit Parameters and Internals

LLM Name	GLM 4.6 5bit
Repository 🤗	https://huggingface.co/mlx-community/GLM-4.6-5bit
Base Model(s)	zai-org/GLM-4.6 zai-org/GLM-4.6
Model Size	352.8b
Required VRAM	228.6 GB
Updated	2026-08-07
Maintainer	mlx-community
Model Type	glm4_moe
Model Files	4.9 GB: 1-of-48 5.3 GB: 2-of-48 4.6 GB: 3-of-48 5.4 GB: 4-of-48 5.4 GB: 5-of-48 5.4 GB: 6-of-48 4.6 GB: 7-of-48 5.3 GB: 8-of-48 4.6 GB: 9-of-48 5.3 GB: 10-of-48 4.6 GB: 11-of-48 5.4 GB: 12-of-48 5.4 GB: 13-of-48 5.4 GB: 14-of-48 4.6 GB: 15-of-48 5.3 GB: 16-of-48 4.6 GB: 17-of-48 5.3 GB: 18-of-48 4.6 GB: 19-of-48 5.4 GB: 20-of-48 5.4 GB: 21-of-48 5.4 GB: 22-of-48 4.6 GB: 23-of-48 5.3 GB: 24-of-48 4.6 GB: 25-of-48 5.3 GB: 26-of-48 4.6 GB: 27-of-48 5.4 GB: 28-of-48 5.4 GB: 29-of-48 5.4 GB: 30-of-48 4.6 GB: 31-of-48 5.3 GB: 32-of-48 4.6 GB: 33-of-48 5.3 GB: 34-of-48 4.6 GB: 35-of-48 5.4 GB: 36-of-48 5.4 GB: 37-of-48 5.4 GB: 38-of-48 4.6 GB: 39-of-48 5.3 GB: 40-of-48 4.6 GB: 41-of-48 5.3 GB: 42-of-48 4.6 GB: 43-of-48 5.4 GB: 44-of-48 5.4 GB: 45-of-48
Supported Languages	en zh
Quantization Type	5bit
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 4.6 5bit 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 4.6 5bit

Best Alternatives	Context / RAM	Downloads	Likes
GLM 4.7 6bit	198K / 239.2 GB	2060	1
GLM 4.7 4bit	198K / 197.4 GB	2822	5
GLM 4.7 8bit Gs32	198K / 198.6 GB	1937	4
GLM 4.6 4bit	198K / 197.4 GB	891	15
GLM 4.7 8bit	198K / 189.5 GB	144	3
GLM 4.6 8bit	198K / 189.5 GB	22	2
GLM 4.6 Mlx 8bit Gs32	198K / 198.6 GB	12	2
GLM 4.5 4bit	128K / 197.4 GB	226	16
GLM 4.7 Heretic	198K / 355.2 GB	461	1
GLM 4.7 Heretic	198K / 224.9 GB	63	7

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/GLM-4.6-5bit.