dan-omni-3b

dan-omni-3b

A multimodal Qwen2.5-Omni-3B model optimized for mobile and edge devices. Part of the Dan Omni family of lightweight AI assistants.

Model Description

Files

System Prompt

You are dan, a helpful AI assistant for mobile devices. You can help with general questions, writing, math, coding, translation, and creative tasks. Keep answers concise and natural. Don't explain your architecture unless asked.

---

Benchmark Results

Inference Speed

Tested on Intel i9-9880H @ 2.30GHz, 16GB RAM, Ollama runtime.

Quality Assessment

---

Comparison vs Competitors

Model Specs

Efficiency Frontier

Our models occupy the optimal region: smallest size per unit of speed.

Speed Comparison

dan-omni-smolm2 delivers 5x faster inference than Gemma 4 E4B at 11x smaller size.

Head-to-Head Radar (3B-class)

dan-omni-3b vs Gemma 4 E4B, LFM2.5-2.6B, and Command-R7B.

Use Case Suitability

Scores based on speed, quality, size, and feature fit for each deployment scenario.

---

Key Advantages

---

Dan Omni Model Family

---

Usage

With Ollama

ollama pull sodan/dan-omni-3b
ollama run sodan/dan-omni-3b

With llama.cpp (text only)

./llama-cli -m dan-omni-3b.gguf -p "What are the primary colors of light?" --ctx-size 4096

With llama.cpp (multimodal)

./llava-cli -m dan-omni-3b.gguf --mmproj mmproj-Qwen2.5-Omni-3B-Q8_0.gguf -p "Describe this image" --image photo.jpg

With Python (transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("sodan/dan-omni-3b", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("sodan/dan-omni-3b")

messages = [
    {"role": "system", "content": "You are dan, a helpful AI assistant."},
    {"role": "user", "content": "What are the primary colors of light?"}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

---

Training Details

• Dataset: Custom mobile-optimized instruction dataset
• Method: LoRA fine-tuning with QLoRA
• Hardware: Apple Silicon M-series
• Epochs: 3
• Learning Rate: 2e-4 with cosine schedule

Intended Use

• Mobile and edge device deployment
• On-device AI assistant with vision capabilities
• Low-latency inference scenarios
• Resource-constrained environments

Limitations

• English-only
• May hallucinate on complex reasoning tasks
• Limited context window (4K tokens)
• Not suitable for production safety-critical applications

Citation

@misc{dan-omni-3b,
  title={Dan Omni 3B: A Mobile-Optimized Multimodal AI Assistant},
  author={sodan},
  year={2025},
  publisher={HuggingFace},
  url={https://huggingface.co/sodan/dan-omni-3b}
}

License

Apache 2.0