LLM EXPLORER 59,358 MODELS INDEXED

Chatglm3 6B by THUDM

By THUDM · 659154 downloads
HF Repo ↗ Copy URL

Chatglm3 6B is an open-source language model by THUDM. Features: 6b LLM, VRAM: 12.5GB, LLM Explorer Score: 0.31, ELO: 970.

  Arxiv:2103.10360   Arxiv:2210.02414   Arxiv:2406.12793   Chatglm   Custom code   En   Endpoints compatible   Glm   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Thudm   Zh
Model Card on HF 🤗: https://huggingface.co/THUDM/chatglm3-6b 

Chatglm3 6B Benchmarks

LMSys ELO 970 vs 1272 (so35) -23.7%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Chatglm3 6B Parameters and Internals

Model Type 
Dialogue, Code Interpreter, Function Call
Use Cases 
Areas:
Research, Commercial applications
Applications:
Dialogue systems, Code interpretation, Function calls
Primary Use Cases:
Smooth dialogue, Low deployment threshold
Additional Notes 
Release notes indicate significant advancements in multiple functions and model series.
Supported Languages 
zh (Chinese), en (English)
Training Details 
Data Sources:
Semantics, Mathematics, Reasoning, Code, Knowledge
Data Volume:
Not specified
Methodology:
More diverse training dataset, more sufficient training steps, and more reasonable training strategy.
Context Length:
32000
Training Time:
Not specified
Hardware Used:
Not specified
Model Architecture:
Not specified
Input Output 
Input Format:
Not specified
Accepted Modalities:
text
Output Format:
Not specified
Performance Tips:
Not specified
Release Notes 
Version:
Not specified
Date:
Not specified
Notes:
More powerful base model with comprehensive function support and more comprehensive open-source series.
LLM NameChatglm3 6B
Repository 🤗https://huggingface.co/THUDM/chatglm3-6b 
Model Size6b
Required VRAM12.5 GB
Updated2025-07-28
MaintainerTHUDM
Model Typechatglm
Model Files  1.8 GB: 1-of-7   2.0 GB: 2-of-7   1.9 GB: 3-of-7   1.8 GB: 4-of-7   2.0 GB: 5-of-7   1.9 GB: 6-of-7   1.1 GB: 7-of-7   1.8 GB: 1-of-7   2.0 GB: 2-of-7   1.9 GB: 3-of-7   1.8 GB: 4-of-7   2.0 GB: 5-of-7   1.9 GB: 6-of-7   1.1 GB: 7-of-7
Supported Languageszh en
Model ArchitectureChatGLMModel
Transformers Version4.30.2
Tokenizer ClassChatGLMTokenizer
Padding Token<unk>
Torch Data Typefloat16

Best Alternatives to Chatglm3 6B

Best Alternatives
Context / RAM
Downloads
Likes
Chatglm2 6B0K / 12.5 GB6173252050
Chatglm2 6B0K / 12.5 GB4476652057
Chatglm3 6B0K / 12.5 GB877141166
Chatglm 6B0K / 13.5 GB12972903
Chatglm 6B0K / 13.5 GB28162862
Codegeex2 6B0K / 12.5 GB435258
Codegeex2 6B0K / 12.5 GB119256
Octogeex0K / 12.5 GB15622