Instructions to use Nitral-AI/Irixxed-Magcap-12B-Slerp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nitral-AI/Irixxed-Magcap-12B-Slerp with Transformers:

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

pipe = pipeline("text-generation", model="Nitral-AI/Irixxed-Magcap-12B-Slerp")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nitral-AI/Irixxed-Magcap-12B-Slerp")
model = AutoModelForCausalLM.from_pretrained("Nitral-AI/Irixxed-Magcap-12B-Slerp", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nitral-AI/Irixxed-Magcap-12B-Slerp with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Nitral-AI/Irixxed-Magcap-12B-Slerp

SGLang

How to use Nitral-AI/Irixxed-Magcap-12B-Slerp 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 "Nitral-AI/Irixxed-Magcap-12B-Slerp" \
    --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": "Nitral-AI/Irixxed-Magcap-12B-Slerp",
		"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 "Nitral-AI/Irixxed-Magcap-12B-Slerp" \
        --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": "Nitral-AI/Irixxed-Magcap-12B-Slerp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nitral-AI/Irixxed-Magcap-12B-Slerp with Docker Model Runner:
```
docker model run hf.co/Nitral-AI/Irixxed-Magcap-12B-Slerp
```

Works great with v1.93 kobold, but appears to be broken when running via v1.95 kobold?

by AutisticPancake - opened Jul 9, 2025

Discussion

AutisticPancake

Jul 9, 2025

I'm not sure if this is my personal issue somehow, but in case if anyone encounters schizo reasoning / looping nonsense - try to roll back to 1.93.
Note: I'm using AMD RX 9070 XT in Vulkan mode. Other models run fine on both versions of kobold, so I suspect this is unique for Irixxed-Magcap at least.

Overall, the model provides a solid RP experience and actually has a nice wiggle room when it comes to prompt writing (I've rewritten the prompt entirely from scratch and it follows everything nicely, generating varied environmental events and NPCs consistently).

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment