Welcome!

• Aqui-open0-2.5: Our flagship open model, with 32B parameters, State-of-the-art performance while using 2x less VRAM. Find more about it here
• Aqui-open0-1 (1.5B, 7.5B, 25B-A8B): The best small open models, trained from scratch. With quantization, the 1.5B can run on a smartphone. Find more about them here
• Aqui-v2-5 series: Our lineup of flagship proprietary models, pushing the frontier in Latin America. Find more about them here [PT-BR]