aquigpt/open1-7.5B-Instruct

Open Models

Aqui-open1 Model Family

We hereby present the first series of small open models by Aqui, trained from scratch and with an MIT license. The open1 family delivers state-of-the-art performance across reasoning, mathematics, and coding tasks while maintaining efficient inference capabilities.

🚀 Released September 7, 2025

🔓 MIT Licensed

⚡ Efficient Architecture

open1-1.5B-Instruct

Ultra-efficient model optimized for edge deployment and real-time applications.

🧠 1.5B parameters

📏 128K context

⚡ Fast inference

View Model

open1-7.5B-Instruct

Balanced model providing exceptional performance across diverse tasks with reasonable compute requirements.

🧠 7.5B parameters

📏 32K context

🎯 High accuracy

View Model

🔜 Coming This Week

Aqui-open1-4x8B — Our biggest non-thinking open model, head-to-head against Qwen3 32B and Llama 3.3 70B. Stay tuned for the most capable open model in the series.

---

Benchmark Performance

1.5B Model Comparison

Metric	open1-1.5B-Instruct	Llama-3.2-1B-Instruct	LFM2-1.2B	Qwen3-1.7B	Gemma-3-1B-it	SmolLM2-1.7B-Instruct
MMLU	58.5	46.6	55.2	59.1	40.1	42.3
GPQA	32.3	28.8	31.5	27.7	21.1	22.1
GSM8K	62.6	35.7	58.3	51.4	59.6	48.2
IFEval	72.7	52.4	74.9	74.0	62.9	56.7
MGSM	59.1	29.1	55.0	66.6	43.6	38.5
Average	57.0	38.5	55.0	55.8	45.5	41.6

7.5B Model Comparison

Benchmark	open1-7.5B-Instruct	Llama-3.1-8B-Instruct	LFM-7B	Qwen3-8B	Gemma-3-12B-it	Nemotron-Nano-9B-v2
MMLU	75.8	68.7	69.4	71.6	72.5	74.5
HumanEval	82.3	71.7	70.1	84.8	84.8	86.2
GPQA Diamond	52.2	25.9	32.9	45.2	34.9	40.8
IFEval	78.9	77.0	71.6	83.4	81.5	84.3
AIME 2025	18.9	4.3	2.1	20.2	18.3	20.1
Average	61.6	49.5	49.2	61.0	58.4	61.2

---

Key Features

🎯 Superior Reasoning

Exceptional performance on MMLU, GPQA, and mathematical reasoning tasks, outperforming models of similar and larger sizes.

⚡ Optimized Architecture

Efficient transformer design enabling fast inference while maintaining high accuracy across diverse benchmarks.

🌍 Multilingual Support

Trained on 20+ languages with robust performance across linguistic boundaries and cultural contexts.

🔓 MIT Licensed

Complete freedom for commercial use, modification, and redistribution with minimal restrictions.

---

Usage

    from transformers import AutoTokenizer, AutoModelForCausalLM
    
# Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("aquigpt/open1-1.5B-Instruct")
model = AutoModelForCausalLM.from_pretrained("aquigpt/open1-1.5B-Instruct")

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

  

Training Details

The open1 models were trained from scratch on a diverse, high-quality dataset spanning code, mathematics, reasoning, and multilingual text. Training utilized advanced techniques including:

• Supervised fine-tuning on instruction-following data
• Constitutional AI for alignment and safety
• Advanced attention mechanisms for extended context
• Multi-stage training with curriculum learning

Note: These models are designed for research and commercial applications. While they demonstrate strong performance, users should conduct appropriate testing for their specific use cases.

Built with ❤️ by the Aqui team • MIT • September 2025