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

Lumina 3 by Ppoyaa

 »  All LLMs  »  Ppoyaa  »  Lumina 3   URL Share it on

  9   
  Autotrain compatible   Conversational   Endpoints compatible   Frankenmoe   Lazymergekit   Merge   Mergekit   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Ppoyaa/Lumina-3 

Lumina 3 Benchmarks

ARC: 71.16 vs 96.7 (so35)-26.4%
HellaSwag: 87.2 vs 95.3 (gpt4)-8.5%
MMLU: 65.52 vs 88.3 (so35)-25.8%
TruthfulQA: 68.25 vs 59 (gpt4)15.7%
WinoGrande: 82.08 vs 87.5 (gpt4)-6.2%
GSM8K: 72.93 vs 96.4 (so35)-24.3%
LLME Score: 0.15498
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Lumina 3 (Ppoyaa/Lumina-3)
🌟 Advertise your project 🚀

Lumina 3 Parameters and Internals

Model Type 
Mixture of Experts (MoE)
Supported Languages 
language (en), proficiency (High)
Training Details 
Methodology:
LazyMergekit
Context Length:
32000
LLM NameLumina 3
Repository 🤗https://huggingface.co/Ppoyaa/Lumina-3 
Model Size7b
Required VRAM37.1 GB
Updated2025-09-23
MaintainerPpoyaa
Model Typemixtral
Model Files  1.9 GB: 1-of-19   2.0 GB: 2-of-19   2.0 GB: 3-of-19   2.0 GB: 4-of-19   2.0 GB: 5-of-19   2.0 GB: 6-of-19   2.0 GB: 7-of-19   2.0 GB: 8-of-19   2.0 GB: 9-of-19   2.0 GB: 10-of-19   2.0 GB: 11-of-19   2.0 GB: 12-of-19   2.0 GB: 13-of-19   2.0 GB: 14-of-19   2.0 GB: 15-of-19   2.0 GB: 16-of-19   2.0 GB: 17-of-19   2.0 GB: 18-of-19   1.2 GB: 19-of-19
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Lumina 3

Best Alternatives
Context / RAM
Downloads
Likes
Multimaster 7B V632K / 142.5 GB97151
Multilingual Mistral32K / 93.5 GB17352
MultiverseBuddy 15B MoE32K / 25.8 GB90
Mini Mixtral V0.232K / 25.8 GB64
Lumina 232K / 37.1 GB50
OpenMistral MoE32K / 48.3 GB12180
Merged Model MoE32K / 53.3 GB41
Laserxtral32K / 48.3 GB81078
BurningBruce 00332K / 48.3 GB17315
RogerWizard 12B MoE32K / 25.8 GB41
Note: green Score (e.g. "73.2") means that the model is better than Ppoyaa/Lumina-3.

Rank the Lumina 3 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? 51534 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.
Release v20241124
  Support LLM Explorer