What are the hardware requirements for Erebus RP Engine 26B A4B?

Erebus RP Engine 26B A4B requires approximately 51.9 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Erebus RP Engine 26B A4B and how large is it?

Erebus RP Engine 26B A4B is developed by Naphula, a model with 26b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Erebus RP Engine 26B A4B?

Erebus RP Engine 26B A4B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Erebus RP Engine 26B A4B by Naphula — VRAM 51.9GB

Name: Erebus RP Engine 26B A4B
Author: Naphula

Erebus RP Engine 26B A4B is an open-source language model by Naphula. Features: 26b LLM, VRAM: 51.9GB, License: apache-2.0, MoE, Merged, LLM Explorer Score: 0.33.

Merged Model Arxiv:2406.11617 Arxiv:2603.04972 All genres Base model:26b-suite/gemory-26... Base model:naphula/goetia-26b-... Base model:ozili/gemma-4-vain-... Base model:readyart/dark-cravi... Base model:readyart/wicked-stu... Base model:submaroon/kitchoon-... Conversational Creative Creative writing Dark writing Dense Eldritchlabs En Endpoints compatible Fiction Fiction story Fiction writing Gemma Gemma4 Horror Image-text-to-text Karcher Moe Moe della Plot generation Region:us Roleplay Roleplaying Romance Rp Safetensors Scene continue Science fiction Sharded Story Story generation Storytelling Sub-plot generation Suspense Swearing Tensorflow Uncensored Unsloth Vivid prosing Vivid writing Writing

Model Card on HF 🤗: https://huggingface.co/Naphula/Erebus-RP-Engine-26B-A4B

Erebus RP Engine 26B A4B Parameters and Internals

LLM Name	Erebus RP Engine 26B A4B
Repository 🤗	https://huggingface.co/Naphula/Erebus-RP-Engine-26B-A4B
Base Model(s)	Naphula/Goetia-26B-A4B-v1.7 Gemory 26B A4B SOMPOA Ozili/Gemma-4-Vain-26B-A4B-GGUF ReadyArt/Wicked-Stuff-26B-A4B-v3.0-Final ReadyArt/Dark-Craving-26B-A4B-v0.1 Kitchoon V3 26B A4B Naphula/Goetia-26B-A4B-v1.7 26B-Suite/Gemory-26B-A4B-SOMPOA Ozili/Gemma-4-Vain-26B-A4B-GGUF ReadyArt/Wicked-Stuff-26B-A4B-v3.0-Final ReadyArt/Dark-Craving-26B-A4B-v0.1 SubMaroon/Kitchoon-V3-26B-A4B
Merged Model	Yes
Model Size	26b
Required VRAM	51.9 GB
Updated	2026-11-03
Maintainer	Naphula
Model Type	gemma4
Model Files	4.7 GB: 1-of-11 4.9 GB: 2-of-11 4.9 GB: 3-of-11 4.9 GB: 4-of-11 4.9 GB: 5-of-11 4.9 GB: 6-of-11 4.9 GB: 7-of-11 4.9 GB: 8-of-11 4.9 GB: 9-of-11 4.9 GB: 10-of-11 3.1 GB: 11-of-11
Supported Languages	en
Model Architecture	Gemma4ForConditionalGeneration
License	apache-2.0
Transformers Version	5.8.0.dev0
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	262144

Rank the Erebus RP Engine 26B A4B 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 Erebus RP Engine 26B A4B

Best Alternatives	Context / RAM	Downloads	Likes
GEV 26B Decide	0K / 51.6 GB	1013022	2316
Gemma 4 26B A4B It	0K / 51.6 GB	10405989	1007
Gemma 4 26B A4B	0K / 51.6 GB	624397	370
Gemma 4 26B A4B It	0K / 51.6 GB	29972	29
Gemma 4 26B A4B StyleTune V2	0K / 53.1 GB	1598	49
Gemma 4 26B A4B	0K / 51.6 GB	3368	19
Gemma 4 26B A4b It Bf16	0K / 51.6 GB	1517	3
Gemma 4 26B A4B NVFP4	0K / 18.8 GB	1424962	126
Gemma 4 26B A4B It FP8 Dynamic	0K / 28.6 GB	1136349	38
Gemma 4 26B A4B It NVFP4	0K / 16.9 GB	154663	21

Note: green Score (e.g. "73.2") means that the model is better than Naphula/Erebus-RP-Engine-26B-A4B.