Instructions to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M

SGLang

How to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with Ollama:
```
ollama run hf.co/Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M
```

Lemonade

How to use Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Erebus-RP-12B-Instruct-2608-v1-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

Erebus-RP-12B-Instruct-2608-v1: Complex Finetune of Gemma 3 12b it Aimed at Enhancing Roleplay and Creative Writing.

"Specialized dataset was used to aggressively make the model roleplay close to how bigger models do, resulting in longer messages and better track of the story."

Quick Overview:

Better roleplay than the base:

Model was trained on carefully selected number of high quality chat logs, filtered only for long term conversations with proper assistant turns.
Entire process was carefully controlled by me to ensure that model can change its writing style without overcooking, this version is a result of repeated attempts until I finally found the right setup.
Reduced refusals due to dataset containing a number of explicit logs.

Quants(this time I will release safetensors and quants in different repos for more convenience):

BF16: Overkill
Q8_0: Highest quality, still overkill
Q6_K: Extremely high quality, near lossless
Q5_K_M: Very high quality, fast, recommended.
Q4_K_M: High quality, very fast, saves a lot of space, recommended.
Q3_K_M: Lower quality, fastest.

Note:

This model turned out pretty well, Nyx is more intelligent and better and instruction following, Erebus is more creative.

I didn't select gemma 4 12b as the base because it was a hell to work with, and was in my observations way more heavily RLed than the gemma 3 12b it, so I took the older generation as the base.

Next I'll probably work on finetuning Mellum 2 12B A2.5B Instruct, also might turn my attention back to Ministral 3 2512. either 3B or 8B I don't know yet,

Downloads last month: 832

GGUF

Model size

12B params

Architecture

gemma3

Hardware compatibility

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for Indexnusrefather/Erebus-RP-12B-Instruct-2608-v1-GGUF

Base model

google/gemma-3-12b-pt

Finetuned

google/gemma-3-12b-it

Finetuned

(397)

this model