aquif-3-mini

A high-performance 3.2B parameter language model based on Meta's Llama 3.2 architecture, optimized for efficiency while maintaining strong capabilities across multiple domains including general knowledge, science, mathematics, coding, and multilingual tasks.

Model Details

Base Model: meta-llama/Llama-3.2-3B
Architecture: Llama
Parameter Count: 3.2 billion parameters
Languages: English, German, Italian, Portuguese, French, Hindi, Spanish, Thai, Chinese, Japanese

Performance Benchmarks

Detailed Benchmark Results

Metric	aquif-3-mini (3.2B)	Llama 3.2 (3.2B)	Qwen3 (4B)	Gemma 3n E4B (8.4B)	SmolLM3 (3.1B)	Phi-4 mini (3.8B)	Granite 3.3 (2.5B)
MMLU (General Knowledge)	67.5	63.4	67.0	64.9	59.5	67.3	55.9
GPQA Diamond (Science)	36.1	29.4	40.7	29.6	35.7	36.9	25.3
AIME 2025 (Competition Math)	9.6	0.3	17.1	11.6	9.3	10.0	2.5
LiveCodeBench (Coding)	15.4	8.3	23.3	14.6	15.2	12.6	9.4
Global MMLU (Multilingual)	58.0	46.8	65.1	53.1	53.5	49.3	49.7
IFEval (Instruction Following)	78.9	71.6	68.9	56.8	76.7	70.1	65.8
BFCL Simple (Tool Calling)	92.3	78.6	81.3	71.8	88.8	70.3	72.2

Key Strengths

• Exceptional Tool Calling: Achieves 92.3% on BFCL Simple benchmark, outperforming all comparison models
• Strong Instruction Following: 78.9% on IFEval, demonstrating reliable adherence to complex instructions
• Comprehensive Knowledge: 70.6% on MMLU, matching or exceeding larger models
• Advanced Reasoning: 46.7% on GPQA Diamond, showing strong scientific reasoning capabilities
• Multilingual Competency: Supports 10 languages with competitive performance

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "aquiffoo/aquif-3-mini"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Generate text
inputs = tokenizer("Explain quantum computing:", return_tensors="pt")
outputs = model.generate(**inputs, max_length=200, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

License

Apache 2.0

Acknowledgements

We gratefully acknowledge:

• Meta AI for the foundational Llama 3.2 architecture and pre-trained weights
• Hugging Face for the transformers library and model hosting platform that enables easy access and deployment

---

For questions, issues, or collaboration opportunities, please reach out through the Hugging Face model page.