LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

GLM 4.6 Mlx 8bit Gs32 by mlx-community

 »  All LLMs  »  mlx-community  »  GLM 4.6 Mlx 8bit Gs32   URL Share it on

  22   

GLM 4.6 Mlx 8bit Gs32 is an open-source language model by mlx-community. Features: 352.8b LLM, VRAM: 198.6GB, Context: 198K, License: mit, Quantized, LLM Explorer Score: 0.22.

  8-bit   8bit 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-mlx-8bit-gs32 

GLM 4.6 Mlx 8bit Gs32 Benchmarks

LLME Score: 0.21843
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GLM 4.6 Mlx 8bit Gs32 (mlx-community/GLM-4.6-mlx-8bit-gs32)
🌟 Advertise your project 🚀

GLM 4.6 Mlx 8bit Gs32 Parameters and Internals

LLM NameGLM 4.6 Mlx 8bit Gs32
Repository 🤗https://huggingface.co/mlx-community/GLM-4.6-mlx-8bit-gs32 
Base Model(s)  zai-org/GLM-4.6   zai-org/GLM-4.6
Model Size352.8b
Required VRAM198.6 GB
Updated2026-04-27
Maintainermlx-community
Model Typeglm4_moe
Model Files  5.0 GB: 1-of-90   4.4 GB: 2-of-90   4.4 GB: 3-of-90   4.4 GB: 4-of-90   4.4 GB: 5-of-90   4.4 GB: 6-of-90   4.4 GB: 7-of-90   4.4 GB: 8-of-90   4.4 GB: 9-of-90   4.4 GB: 10-of-90   4.4 GB: 11-of-90   4.4 GB: 12-of-90   4.4 GB: 13-of-90   4.4 GB: 14-of-90   4.4 GB: 15-of-90   4.4 GB: 16-of-90   4.4 GB: 17-of-90   4.4 GB: 18-of-90   4.4 GB: 19-of-90   4.4 GB: 20-of-90   4.4 GB: 21-of-90   4.4 GB: 22-of-90   4.4 GB: 23-of-90   4.4 GB: 24-of-90   4.4 GB: 25-of-90   4.4 GB: 26-of-90   4.4 GB: 27-of-90   4.4 GB: 28-of-90   4.4 GB: 29-of-90   4.4 GB: 30-of-90   4.4 GB: 31-of-90   4.4 GB: 32-of-90   4.4 GB: 33-of-90   4.4 GB: 34-of-90   4.4 GB: 35-of-90   4.4 GB: 36-of-90   4.4 GB: 37-of-90   4.4 GB: 38-of-90   4.4 GB: 39-of-90   4.4 GB: 40-of-90   4.4 GB: 41-of-90   4.4 GB: 42-of-90   4.4 GB: 43-of-90   4.4 GB: 44-of-90   4.4 GB: 45-of-90
Supported Languagesen zh
Quantization Type8bit
Model ArchitectureGlm4MoeForCausalLM
Licensemit
Context Length202752
Model Max Length202752
Transformers Version4.54.0
Vocabulary Size151552
Torch Data Typebfloat16

Best Alternatives to GLM 4.6 Mlx 8bit Gs32

Best Alternatives
Context / RAM
Downloads
Likes
GLM 4.7 4bit198K / 197.4 GB37075
GLM 4.7 8bit Gs32198K / 198.6 GB17584
GLM 4.7 8bit198K / 189.5 GB3064
GLM 4.6 4bit198K / 197.4 GB131515
GLM 4.6 5bit198K / 228.6 GB3463
GLM 4.6 8bit198K / 189.5 GB212
GLM 4.5 4bit128K / 197.4 GB19116
GLM 4.6 Bf16198K / 232.5 GB273
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/GLM-4.6-mlx-8bit-gs32.

Rank the GLM 4.6 Mlx 8bit Gs32 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53310 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer