What are the hardware requirements for Erebus RP 12B Instruct 2608 V1?

Erebus RP 12B Instruct 2608 V1 requires approximately 23.4 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Erebus RP 12B Instruct 2608 V1 and how large is it?

Erebus RP 12B Instruct 2608 V1 is developed by Indexnusrefather, a model with 12b 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 12B Instruct 2608 V1?

Erebus RP 12B Instruct 2608 V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Erebus RP 12B Instruct 2608 V1 by Indexnusrefather — VRAM 23.4GB, 128K context

Name: Erebus RP 12B Instruct 2608 V1
Author: Indexnusrefather

Erebus RP 12B Instruct 2608 V1 is an open-source language model by Indexnusrefather. Features: 12b LLM, VRAM: 23.4GB, Context: 128K, License: gemma, Instruction-Based, LLM Explorer Score: 0.24.

Base model:finetune:google/gem... Base model:google/gemma-3-12b-... Conversational Creative Creative writing En Endpoints compatible Erp Experimental Finetuned Gemma3 Gemma3 text Instruct Region:us Rich worldbuilding Roleplay Rp Safetensors Sharded Tensorflow V1 Writer

Model Card on HF 🤗: https://huggingface.co/Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1

Erebus RP 12B Instruct 2608 V1 Parameters and Internals

LLM Name	Erebus RP 12B Instruct 2608 V1
Repository 🤗	https://huggingface.co/Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1
Model Name	C:\Users\vHDd3\Downloads\Erebus-RP-12B-Instruct-2608-v1
Base Model(s)	Gemma 3 12B It google/gemma-3-12b-it
Model Size	12b
Required VRAM	23.4 GB
Updated	2026-08-15
Maintainer	Indexnusrefather
Model Type	gemma3_text
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-5 4.9 GB: 2-of-5 4.9 GB: 3-of-5 4.9 GB: 4-of-5 3.8 GB: 5-of-5
Supported Languages	en
Model Architecture	Gemma3ForCausalLM
License	gemma
Context Length	131072
Model Max Length	131072
Tokenizer Class	GemmaTokenizer
Padding Token	<pad>
Vocabulary Size	262208
Torch Data Type	bfloat16

Rank the Erebus RP 12B Instruct 2608 V1 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

Quantized Models of the Erebus RP 12B Instruct 2608 V1

Model	Likes	Downloads	VRAM
... 12B Instruct 2608 V1 Mlx 6Bit	1	225	9 GB

Best Alternatives to Erebus RP 12B Instruct 2608 V1

Best Alternatives	Context / RAM	Downloads	Likes
GaMS3 12B Instruct	128K / 23.4 GB	4238	5
... 12B Instruct 2608 V1 Mlx 6Bit	128K / 9.6 GB	225	1

Note: green Score (e.g. "73.2") means that the model is better than Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1.