What are the hardware requirements for OPT 2.7B Nerys V2?

OPT 2.7B Nerys V2 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 Nerys V2 and how large is it?

OPT 2.7B Nerys V2 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 Nerys V2 perform on standard benchmarks?

OPT 2.7B Nerys V2 has the following published scores: MMLU 26.44. Compare against reference models on this page or on the LLM Explorer leaderboards.

OPT 2.7B Nerys V2 by KoboldAI — VRAM 5.3GB, 2K context

Name: OPT 2.7B Nerys V2
Author: KoboldAI

OPT 2.7B Nerys V2 is an open-source language model by KoboldAI. Features: 2.7b LLM, VRAM: 5.3GB, Context: 2K, License: other, LLM Explorer Score: 0.07, Arc: 33.3, HellaSwag: 61.2, MMLU: 26.4, GSM8K: 0.3.

Arxiv:2205.01068 En Endpoints compatible Opt Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/KoboldAI/OPT-2.7B-Nerys-v2

OPT 2.7B Nerys V2 Parameters and Internals

Model Type

text generation

Use Cases

Applications:

text generation

Limitations:

Bias may exist based on gender, profession, race, and religion.

Training Details

Data Sources:

Pike dataset: 2500 ebooks, CYOA dataset: CYS, Manga-v1 dataset: 50 Asian Light Novels

Methodology:

finetuning

Responsible Ai Considerations

Fairness:

Bias may exist based on gender, profession, race, and religion.

LLM Name	OPT 2.7B Nerys V2
Repository 🤗	https://huggingface.co/KoboldAI/OPT-2.7B-Nerys-v2
Model Size	2.7b
Required VRAM	5.3 GB
Updated	2026-07-16
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 Nerys V2 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 Nerys V2

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 Erebus	2K / 5.3 GB	380	42
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-Nerys-v2.