AionLabs: Aion-1.0-Mini

Aion-1.0-Mini 32B parameter model is a distilled version of the DeepSeek-R1 model, designed for strong performance in reasoning domains such as mathematics, coding, and logic. It is a modified variant of a FuseAI model that outperforms R1-Distill-Qwen-32B and R1-Distill-Llama-70B, with benchmark results available on its Hugging Face page, independently replicated for verification.

Aion-1.0-Mini has a 16,384 token context window.

Aion-3.0-Mini, Aion-3.0, Aion-2.0 and 1 more are other text models from Aion Labs.

Aion-1.0-Mini was released on February 4, 2025.