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

Gemma 3 40B by ddh0

 »  All LLMs  »  ddh0  »  Gemma 3 40B   URL Share it on

  0   

Gemma 3 40B is an open-source language model by ddh0. Features: 27b LLM, VRAM: 79.6GB, Context: 128K, License: gemma, LLM Explorer Score: 0.2.

Base model:google/gemma-3-27b-... Base model:google/gemma-3-27b-... Base model:merge:google/gemma-... Base model:merge:google/gemma-...   Gemma3 text   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ddh0/gemma-3-40b 

Gemma 3 40B Benchmarks

LLME Score: 0.19921
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 3 40B (ddh0/gemma-3-40b)
🌟 Advertise your project 🚀

Gemma 3 40B Parameters and Internals

LLM NameGemma 3 40B
Repository 🤗https://huggingface.co/ddh0/gemma-3-40b 
Base Model(s)  google/gemma-3-27b-it   google/gemma-3-27b-pt   google/gemma-3-27b-it   google/gemma-3-27b-pt
Model Size27b
Required VRAM79.6 GB
Updated2025-07-15
Maintainerddh0
Model Typegemma3_text
Model Files  9.9 GB: 1-of-9   9.9 GB: 2-of-9   9.8 GB: 3-of-9   9.8 GB: 4-of-9   9.9 GB: 5-of-9   9.8 GB: 6-of-9   9.8 GB: 7-of-9   9.9 GB: 8-of-9   0.8 GB: 9-of-9
Model ArchitectureGemma3ForCausalLM
Licensegemma
Context Length131072
Model Max Length131072
Transformers Version4.53.1
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size262145
Torch Data Typebfloat16

Best Alternatives to Gemma 3 40B

Best Alternatives
Context / RAM
Downloads
Likes
Fanar 2 27B Instruct128K / 54.4 GB610811
YanoljaNEXT Rosetta 27B 2511128K / 57.2 GB4935
Medgemma 27B Text Heretic Med128K / 54.4 GB195
Medgemma 27B Text It128K / 54.4 GB6187
Gemma 3 27B It Abliterated V2128K / 108.9 GB24520
Medgemma 27B Text It Bf16128K / 56.8 GB803
Gemma 3 27B Novision128K / 54.4 GB2543
...a 3 27B Experiment Storyteller128K / 54.4 GB50
...emma 3 27B Experiment V2 Merge128K / 106.1 GB50
Gemma 3 27B Fujin128K / 54.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than ddh0/gemma-3-40b.

Rank the Gemma 3 40B 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? 53999 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