Instructions to use suayptalha/Arcana-Qwen3-2.4B-A0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use suayptalha/Arcana-Qwen3-2.4B-A0.6B with Transformers:

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

pipe = pipeline("text-generation", model="suayptalha/Arcana-Qwen3-2.4B-A0.6B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("suayptalha/Arcana-Qwen3-2.4B-A0.6B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use suayptalha/Arcana-Qwen3-2.4B-A0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "suayptalha/Arcana-Qwen3-2.4B-A0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "suayptalha/Arcana-Qwen3-2.4B-A0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/suayptalha/Arcana-Qwen3-2.4B-A0.6B

SGLang

How to use suayptalha/Arcana-Qwen3-2.4B-A0.6B 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 "suayptalha/Arcana-Qwen3-2.4B-A0.6B" \
    --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": "suayptalha/Arcana-Qwen3-2.4B-A0.6B",
		"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 "suayptalha/Arcana-Qwen3-2.4B-A0.6B" \
        --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": "suayptalha/Arcana-Qwen3-2.4B-A0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use suayptalha/Arcana-Qwen3-2.4B-A0.6B with Docker Model Runner:
```
docker model run hf.co/suayptalha/Arcana-Qwen3-2.4B-A0.6B
```

"We are all experts at something, but we’re all also beginners at something else."

— The Imitation Game (2014)

Arcana Qwen3 2.4B A0.6B

This is a MoE (Mixture of Experts) Qwen3 model which has total number of 2.4B parameters and 0.6B for each of 4 experts. All the expert models can be seen below. This model aims to provide more accurate results with more efficiency and less memory usage!

Expert Models:

Key Training Parameters (SFTConfig)

per_device_train_batch_size = 2
gradient_accumulation_steps = 4
warmup_steps = 5
num_train_epochs = 1
learning_rate = 2e-5
optim = "adamw_8bit"
weight_decay = 0.01
seed = 3407

Coding:

suayptalha/Qwen3-0.6B-Code-Expert

This model was fully fine-tuned with BF16 on first 20k rows of nvidia/OpenCodeReasoning dataset for 1 epoch.

Math:

suayptalha/Qwen3-0.6B-Math-Expert

This model was fully fine-tuned with BF16 on entire unsloth/OpenMathReasoning-mini dataset for 1 epoch.

Medical:

suayptalha/Qwen3-0.6B-Medical-Expert

This model was fully fine-tuned with BF16 on first 20k rows of FreedomIntelligence/medical-o1-reasoning-SFT dataset for 1 epoch.

Instruction Following:

Qwen/Qwen3-0.6B

Qwen/Qwen3-0.6B model was directly used for this expert, no fine-tune was applied.

Router Model:

The router model can be found here which was trained version of distilbert/distilbert-base-uncased on 7 different datasets.

Usage:

import torch
from huggingface_hub import snapshot_download
from transformers import AutoModelForCausalLM, AutoTokenizer

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

local_dir = snapshot_download(
    repo_id="suayptalha/Qwen3-2.4B-A0.6B",
)

model = AutoModelForCausalLM.from_pretrained(
    local_dir,
    trust_remote_code=True,
)
tokenizer = AutoTokenizer.from_pretrained(
    local_dir,
)

model.to(device)
model.eval()

prompt = "I have pain in my chest, what should I do?"
messages = [{"role": "user", "content": prompt}]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

with torch.no_grad():
    output_ids = model.generate(
        text=prompt,
        max_new_tokens=1024,
        temperature=0.6,
        top_p=0.95,
    )
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
print(output_text)