What are the hardware requirements for OPT 13B Nerys V2?

OPT 13B Nerys V2 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 Nerys V2 and how large is it?

OPT 13B Nerys V2 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 Nerys V2 perform on standard benchmarks?

OPT 13B Nerys V2 has the following published scores: MMLU 25.36. Compare against reference models on this page or on the LLM Explorer leaderboards.

OPT 13B Nerys V2 by KoboldAI — VRAM 25.7GB, 2K context

Name: OPT 13B Nerys V2
Author: KoboldAI

OPT 13B Nerys V2 is an open-source language model by KoboldAI. Features: 13b LLM, VRAM: 25.7GB, Context: 2K, License: other, LLM Explorer Score: 0.07, Arc: 39.7, HellaSwag: 70.5, MMLU: 25.4, GSM8K: 0.2.

Arxiv:2205.01068 En Endpoints compatible Opt Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/KoboldAI/OPT-13B-Nerys-v2

OPT 13B Nerys V2 Parameters and Internals

Model Type

text generation

Use Cases

Areas:

Text Generation

Limitations:

Bias in gender, profession, race, and religion

Training Details

Data Sources:

Pike dataset, CYS dataset, Manga-v1 dataset

Data Volume:

2500 ebooks

Methodology:

Finetuning

Model Architecture:

Transformer

LLM Name	OPT 13B Nerys V2
Repository 🤗	https://huggingface.co/KoboldAI/OPT-13B-Nerys-v2
Model Size	13b
Required VRAM	25.7 GB
Updated	2026-08-06
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 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 13B Nerys V2

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 Erebus	2K / 25.7 GB	413	261
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-Nerys-v2.