What are the hardware requirements for OPT 2.7B Erebus?

OPT 2.7B Erebus requires approximately 5.3 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 2.7B Erebus and how large is it?

OPT 2.7B Erebus is developed by KoboldAI, a model with 2.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does OPT 2.7B Erebus perform on standard benchmarks?

OPT 2.7B Erebus has the following published scores: MMLU 26.7. Compare against reference models on this page or on the LLM Explorer leaderboards.

OPT 2.7B Erebus by KoboldAI — VRAM 5.3GB, 2K context

Name: OPT 2.7B Erebus
Author: KoboldAI

OPT 2.7B Erebus is an open-source language model by KoboldAI. Features: 2.7b LLM, VRAM: 5.3GB, Context: 2K, License: other, LLM Explorer Score: 0.08, Arc: 34.4, HellaSwag: 60.9, MMLU: 26.7, GSM8K: 0.3.

Arxiv:2205.01068 Deploy:azure En Opt Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/KoboldAI/OPT-2.7B-Erebus

OPT 2.7B Erebus Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Text generation

Limitations:

Model is not suitable for use by minors, Strong NSFW bias

Additional Notes

The model outputs X-rated content.

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 2.7B Erebus
Repository 🤗	https://huggingface.co/KoboldAI/OPT-2.7B-Erebus
Model Size	2.7b
Required VRAM	5.3 GB
Updated	2026-08-05
Maintainer	KoboldAI
Model Type	opt
Model Files	5.3 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 2.7B 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 2.7B Erebus

Best Alternatives	Context / RAM	Downloads	Likes
LLmRa 2.7B	2K / 10.6 GB	642	1
Opt 2.7B	2K / 5.3 GB	35827	89
OPT 2.7B Nerybus Mix	2K / 5.5 GB	194	10
OPT 2.7B Nerys V2	2K / 5.3 GB	124	6
Opt 2.7B Realtime Chat V2	2K / 11.1 GB	9	0
LongForm OPT 2.7B	2K / 5.3 GB	5	3
Opt 2.7B Wikitext2	2K / 11.1 GB	6	0
Opt 2.7B Realtime Chat	2K / 11.1 GB	7	2
Opt Peter 2.7B	2K / 10.6 GB	2	2
Opt 2.7B AWQ	2K / 1.6 GB	5	0

Note: green Score (e.g. "73.2") means that the model is better than KoboldAI/OPT-2.7B-Erebus.