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

OPT 30B Erebus by KoboldAI

 »  All LLMs  »  KoboldAI  »  OPT 30B Erebus   URL Share it on

  1712   

OPT 30B Erebus is an open-source language model by KoboldAI. Features: 30b LLM, VRAM: 36GB, Context: 2K, License: other, HF Score: 38.5, LLM Explorer Score: 0.11, Arc: 36.7, HellaSwag: 65.6, MMLU: 24.8, TruthfulQA: 38.8, WinoGrande: 65.1, GSM8K: 0.2.

  Arxiv:2205.01068   Autotrain compatible   En   Opt   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/KoboldAI/OPT-30B-Erebus 

OPT 30B Erebus Benchmarks

ARC: 36.69 vs 96.7 (so35)-62.1%
HellaSwag: 65.6 vs 95.3 (gpt4)-31.2%
MMLU: 24.8 vs 88.3 (so35)-71.9%
TruthfulQA: 38.76 vs 59 (gpt4)-34.3%
WinoGrande: 65.11 vs 87.5 (gpt4)-25.6%
GSM8K: 0.23 vs 96.4 (so35)-99.8%
LLME Score: 0.11089
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OPT 30B Erebus (KoboldAI/OPT-30B-Erebus)
🌟 Advertise your project 🚀

OPT 30B Erebus Parameters and Internals

Model Type 
text generation
Additional Notes 
Warning: THIS model has a very strong NSFW bias.
Training Details 
Data Sources:
Literotica (everything with 4.5/5 or higher), Sexstories (everything with 90 or higher), Dataset-G (private dataset of X-rated stories), Doc's Lab (all stories), Pike Dataset (novels with 'adult' rating), SoFurry (collection of various animals)
LLM NameOPT 30B Erebus
Repository 🤗https://huggingface.co/KoboldAI/OPT-30B-Erebus 
Model Size30b
Required VRAM36 GB
Updated2025-09-28
MaintainerKoboldAI
Model Typeopt
Model Files  1.0 GB: 1-of-74   0.6 GB: 2-of-74   0.8 GB: 3-of-74   0.9 GB: 4-of-74   0.7 GB: 5-of-74   0.8 GB: 6-of-74   0.9 GB: 7-of-74   0.7 GB: 8-of-74   0.8 GB: 9-of-74   0.9 GB: 10-of-74   0.7 GB: 11-of-74   0.8 GB: 12-of-74   0.9 GB: 13-of-74   0.7 GB: 14-of-74   0.8 GB: 15-of-74   0.9 GB: 16-of-74   0.7 GB: 17-of-74   0.8 GB: 18-of-74   0.9 GB: 19-of-74   0.7 GB: 20-of-74   0.8 GB: 21-of-74   0.9 GB: 22-of-74   0.7 GB: 23-of-74   0.8 GB: 24-of-74   0.9 GB: 25-of-74   0.7 GB: 26-of-74   0.8 GB: 27-of-74   0.9 GB: 28-of-74   0.7 GB: 29-of-74   0.8 GB: 30-of-74   0.9 GB: 31-of-74   0.7 GB: 32-of-74   0.8 GB: 33-of-74   0.9 GB: 34-of-74   0.7 GB: 35-of-74   0.8 GB: 36-of-74   0.9 GB: 37-of-74   0.7 GB: 38-of-74   0.8 GB: 39-of-74   0.9 GB: 40-of-74   0.7 GB: 41-of-74   0.8 GB: 42-of-74   0.9 GB: 43-of-74   0.7 GB: 44-of-74   0.8 GB: 45-of-74
Supported Languagesen
Model ArchitectureOPTForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.25.1
Vocabulary Size50265
Torch Data Typefloat16
Activation Functionrelu

Best Alternatives to OPT 30B Erebus

Best Alternatives
Context / RAM
Downloads
Likes
Galpaca 30B MiniOrca2K / 59.6 GB17421
Galpaca 30B2K / 60.8 GB83655
Opt Iml Max 30B2K / 60.1 GB91135
Opt 30B2K / 60.1 GB8011136
...alactica 30B Evol Instruct 70K2K / 60.1 GB161823
Opt Iml 30B2K / 60.1 GB4774
Galactica 30B2K / 60.8 GB67440
Dalio Io 30B Cp15002K / 121.7 GB110
Galactica 30B2K /  GB51
...ed 30b Bs4 4e 6lr 2epoch Seed12K / 121.7 GB90
Note: green Score (e.g. "73.2") means that the model is better than KoboldAI/OPT-30B-Erebus.

Rank the OPT 30B Erebus 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? 52394 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