What are the hardware requirements for GLM 4.6 Bf16?

GLM 4.6 Bf16 requires approximately 232.5 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 4.6 Bf16 and how large is it?

GLM 4.6 Bf16 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 Bf16?

GLM 4.6 Bf16 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 4.6 Bf16 by mlx-community — VRAM 232.5GB, 198K context

Name: GLM 4.6 Bf16
Author: mlx-community

GLM 4.6 Bf16 is an open-source language model by mlx-community. Features: 352.8b LLM, VRAM: 232.5GB, Context: 198K, License: mit, LLM Explorer Score: 0.2.

Base model:finetune:zai-org/gl... Base model:zai-org/glm-4.6 Conversational En Glm4 moe Mlx Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/mlx-community/GLM-4.6-bf16

GLM 4.6 Bf16 Parameters and Internals

LLM Name	GLM 4.6 Bf16
Repository 🤗	https://huggingface.co/mlx-community/GLM-4.6-bf16
Base Model(s)	zai-org/GLM-4.6 zai-org/GLM-4.6
Model Size	352.8b
Required VRAM	232.5 GB
Updated	2026-08-08
Maintainer	mlx-community
Model Type	glm4_moe
Model Files	3.8 GB: 1-of-135 5.0 GB: 2-of-135 5.3 GB: 3-of-135 5.3 GB: 4-of-135 5.0 GB: 5-of-135 5.3 GB: 6-of-135 5.3 GB: 7-of-135 5.0 GB: 8-of-135 5.3 GB: 9-of-135 5.3 GB: 10-of-135 5.0 GB: 11-of-135 5.3 GB: 12-of-135 5.3 GB: 13-of-135 5.0 GB: 14-of-135 5.3 GB: 15-of-135 5.3 GB: 16-of-135 5.0 GB: 17-of-135 5.3 GB: 18-of-135 5.3 GB: 19-of-135 5.0 GB: 20-of-135 5.3 GB: 21-of-135 5.3 GB: 22-of-135 5.0 GB: 23-of-135 5.3 GB: 24-of-135 5.3 GB: 25-of-135 5.0 GB: 26-of-135 5.3 GB: 27-of-135 5.3 GB: 28-of-135 5.0 GB: 29-of-135 5.3 GB: 30-of-135 5.3 GB: 31-of-135 5.0 GB: 32-of-135 5.3 GB: 33-of-135 5.3 GB: 34-of-135 5.0 GB: 35-of-135 5.3 GB: 36-of-135 5.3 GB: 37-of-135 5.0 GB: 38-of-135 5.3 GB: 39-of-135 5.3 GB: 40-of-135 5.0 GB: 41-of-135 5.3 GB: 42-of-135 5.3 GB: 43-of-135 5.0 GB: 44-of-135 5.3 GB: 45-of-135
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 4.6 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 4.6 Bf16

Model	Likes	Downloads	VRAM
GLM 4.6 8bit	2	22	189 GB

Best Alternatives to GLM 4.6 Bf16

Best Alternatives	Context / RAM	Downloads	Likes
GLM 4.7 Heretic	198K / 355.2 GB	461	1
GLM 4.7 Heretic	198K / 224.9 GB	63	7
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 5bit	198K / 228.6 GB	125	3
GLM 4.6 Mlx 8bit Gs32	198K / 198.6 GB	12	2

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/GLM-4.6-bf16.