Instructions to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with Transformers:

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

pipe = pipeline("image-text-to-text", model="0xA50C1A1/Ministral-3-8B-Nymphaea-RP")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("0xA50C1A1/Ministral-3-8B-Nymphaea-RP")
model = AutoModelForMultimodalLM.from_pretrained("0xA50C1A1/Ministral-3-8B-Nymphaea-RP", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP 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 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0
# Run inference directly in the terminal:
llama cli -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0
# Run inference directly in the terminal:
llama cli -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

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 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

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 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

Use Docker

docker model run hf.co/0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

LM Studio
Jan

vLLM

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xA50C1A1/Ministral-3-8B-Nymphaea-RP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xA50C1A1/Ministral-3-8B-Nymphaea-RP",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

SGLang

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP 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 "0xA50C1A1/Ministral-3-8B-Nymphaea-RP" \
    --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": "0xA50C1A1/Ministral-3-8B-Nymphaea-RP",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "0xA50C1A1/Ministral-3-8B-Nymphaea-RP" \
        --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": "0xA50C1A1/Ministral-3-8B-Nymphaea-RP",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with Ollama:
```
ollama run hf.co/0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0
```

Unsloth Studio

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for 0xA50C1A1/Ministral-3-8B-Nymphaea-RP to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for 0xA50C1A1/Ministral-3-8B-Nymphaea-RP to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for 0xA50C1A1/Ministral-3-8B-Nymphaea-RP to start chatting

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with Docker Model Runner:
```
docker model run hf.co/0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0
```

Lemonade

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

Run and chat with the model

lemonade run user.Ministral-3-8B-Nymphaea-RP-Q8_0

List all available models

lemonade list

Hermes Agent

How to use 0xA50C1A1/Ministral-3-8B-Nymphaea-RP with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default 0xA50C1A1/Ministral-3-8B-Nymphaea-RP:Q8_0

Run Hermes

hermes

Atomic Chat

Ministral-3-8B-Nymphaea-RP

A fine-tune of Ministral 3 8B Instruct 2512 for roleplay and creative writing.

A good choice for low-VRAM, I think. IMAO, better than Llama 3.3 8B Instruct.

The SillyTavern preset is available here. For custom presets, please use the Mistral V7-Tekken instruct template.

Chat Example

A Borat-style attack on the SMUT bot. Tested at Q8_0 quantization.

GGUF

Here is my custom mixed-quant GGUF, optimized for 8/12GB VRAM. If you need mmproj, it's available here.

GGUF recipe

llama-quantize \
  --imatrix imatrix.gguf \
  --token-embedding-type q8_0 \
  --output-tensor-type q8_0 \
  --tensor-type ".*attn_q.weight=q8_0" \
  --tensor-type ".*attn_k.weight=q8_0" \
  --tensor-type ".*attn_v.weight=q5_k" \
  --tensor-type ".*attn_output.weight=q5_k" \
  --tensor-type ".*ffn_up.weight=iq4_nl" \
  --tensor-type ".*ffn_gate.weight=iq4_nl" \
  --tensor-type ".*ffn_down.weight=q5_k" \
  Ministral-3-8B-Nymphaea-RP.F16.gguf \
  Ministral-3-8B-Nymphaea-RP.Q5_Mix.gguf \
  q5_k

Imatrix file for making your own quants is available here. I used this calibration dataset to create it, expanding it with RP and creative writing data (about 400k tokens).

Training Notes

Trained on the latest iteration of my Darkmere dataset. This version features expanded genre variety, built upon a mix of manually curated synthetics and human-written stories.

The base weights are abliterated via Heretic prior to fine-tuning, so this fine-tune is quite uncensored.

Training Specs

Method:

Training Method: DoRA (Weight-Decomposed LoRA)
Target Modules all-linear
LoRA Rank: 64
LoRA Alpha: 64
LoRA Dropout: 0.05

Hyperparameters:

Batch Size: 2 (Per-device)
Gradient Accumulation: 2
Epochs: 2
Learning Rate: 1e-4
Optimizer: adamw_torch_fused
LR Scheduler: cosine
Noise Level: neftune_noise_alpha=5

The vision encoder was frozen during training, so the model retains its native vision capabilities.

Special Thanks

This fine-tune wouldn't be possible without the incredible work of the community:

p-e-w for developing Heretic - an essential tool for censorship removal.
SicariusSicariiStuff for developing SLOP_Detector script.
Mistral AI for their Ministral 3 weights.
AMD for their Instinct™ MI300X GPU.

Downloads last month: 740

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for 0xA50C1A1/Ministral-3-8B-Nymphaea-RP

Base model

0xA50C1A1/Ministral-3-8B-Instruct-2512-BF16-SOM-MPOA

Quantized

(3)

this model

Quantizations

2 models