What are the hardware requirements for OPT 13B Erebus?

OPT 13B Erebus requires approximately 25.7 GB of VRAM and supports a context window of 2K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OPT 13B Erebus and how large is it?

OPT 13B Erebus is developed by KoboldAI, a model with 13b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does OPT 13B Erebus perform on standard benchmarks?

OPT 13B Erebus has the following published scores: MMLU 25.32. Compare against reference models on this page or on the LLM Explorer leaderboards.

OPT 13B Erebus by KoboldAI — VRAM 25.7GB, 2K context

Name: OPT 13B Erebus
Author: KoboldAI

OPT 13B Erebus is an open-source language model by KoboldAI. Features: 13b LLM, VRAM: 25.7GB, Context: 2K, License: other, LLM Explorer Score: 0.08, Arc: 40, HellaSwag: 70.1, MMLU: 25.3, GSM8K: 0.8.

Arxiv:2205.01068 En Opt Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/KoboldAI/OPT-13B-Erebus

OPT 13B 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 Name	OPT 13B Erebus
Repository 🤗	https://huggingface.co/KoboldAI/OPT-13B-Erebus
Model Size	13b
Required VRAM	25.7 GB
Updated	2026-07-25
Maintainer	KoboldAI
Model Type	opt
Model Files	25.7 GB
Supported Languages	en
Model Architecture	OPTForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.21.2
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	</s>
End of Sentence Token	</s>
Unk Token	</s>
Vocabulary Size	50265
Torch Data Type	float16
Activation Function	relu
Errors	replace

Rank the OPT 13B Erebus capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to OPT 13B Erebus

Best Alternatives	Context / RAM	Downloads	Likes
Emoopt 13B	2K / 25.7 GB	8	0
OPT 13B Nerybus Mix	2K / 26.4 GB	171	36
Opt 13B	2K / 25.8 GB	11924	65
OPT 13B Nerys V2	2K / 25.7 GB	110	12
Basic Facebook 13B	2K / 25.8 GB	15	1
Opt 13B	2K / 26.3 GB	7	1
OPT 13B Nerybus Mix 4bit 128g	2K / 7.3 GB	58	6
OPT 13B Erebus 4bit 128g	2K / 7.3 GB	8	17

Note: green Score (e.g. "73.2") means that the model is better than KoboldAI/OPT-13B-Erebus.