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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🧠 Irixxed-Magcap-12B-Slerp

Merge power meets pure reasoning finesse.

Starting with Violet_Magcap-12B, and blended in the smooth strength of Irix-12B-Model_Stock.

No gimmicks, just synergy:
A classic Slerp merge crafted for sharp reasoning and solid performance—because why settle for one when you can have both?

ChatML Format

⚙️ Usage Presets

🎛️ SillyTavern Presets

💾 Quantized Versions

Q8_0 (GGUF)
Q5_K_M (GGUF)

Q4_K_M (GGUF)
4bpw (ExL2)

🛠️ Model Details

Feature	Description
Base Models	Violet_Magcap-12B + Irix-12B-Model_Stock
Size	12B Parameters
Library	Transformers
Merge Type	Regular Slerp

📦 Reasoning Information

Reasoning Block + Prefix

Quick Reply's

⚙️ Merge-kit Config

  slices:
  - sources:
      - model: DreadPoor/Irix-12B-Model_Stock
        layer_range: [0, 40]
      - model: Nitral-AI/Violet_Magcap-12B
        layer_range: [0, 40]
merge_method: slerp
base_model: DreadPoor/Irix-12B-Model_Stock
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.50
dtype: bfloat16

🌀 Vibe Check

Synergy in code, clarity in reasoning.
Use it wisely—or just enjoy the smooth ride.

🧬 Created by: Nitral-AI 💖 Support on Ko-fi

Downloads last month: 25

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for Nitral-AI/Irixxed-Magcap-12B-Slerp

DreadPoor/Irix-12B-Model_Stock

Nitral-AI/Violet_Magcap-12B

Merge model

this model

Merges

2 models

Quantizations

14 models