Local execution eliminates data transmission and token-based usage fees
We are so happy to announce our new model Aion 1.0 today!
Our team at AI Frontiers Lab at Microsoft Research had been cooking hard on this for quite a while.
Aion 1.0 is 14B model that can run locally with reasoning + tool calling capabilities. You can choose whatever agentic harness you like or make your own. Calls to the model never leaves your device and no one charges you for any tokens you use 🥳.
Congratulations to @BehlHarkirat , @snakshay, @AhmedHAwadallah, Caio Medes, @YashLara, Karan Gupta, @yashpandya96, Amir Saeidi, @CameronPashmina and our whole team!
We are so happy to announce our new model Aion 1.0 today!
Our team at AI Frontiers Lab at Microsoft Research had been cooking hard on this for quite a while.
Aion 1.0 is 14B model that can run locally with reasoning + tool calling capabilities. You can choose whatever agentic harness you like or make your own. Calls to the model never leaves your device and no one charges you for any tokens you use 🥳.
@sytelus congrats! any relationship with the MAI series, or totally independent?
also is it on HF 👀
We are so happy to announce our new model Aion 1.0 today!
Our team at AI Frontiers Lab at Microsoft Research had been cooking hard on this for quite a while.
Aion 1.0 is 14B model that can run locally with reasoning + tool calling capabilities. You can choose whatever agentic harness you like or make your own. Calls to the model never leaves your device and no one charges you for any tokens you use 🥳.
Local execution eliminates data transmission and token-based usage fees
We are so happy to announce our new model Aion 1.0 today!
Our team at AI Frontiers Lab at Microsoft Research had been cooking hard on this for quite a while.
Aion 1.0 is 14B model that can run locally with reasoning + tool calling capabilities. You can choose whatever agentic harness you like or make your own. Calls to the model never leaves your device and no one charges you for any tokens you use 🥳.
Many users praised Microsoft's Aion 1.0 as a practical 14B local model because its size and built-in reasoning plus tool calling make it well suited for agent tasks without needing frontier-scale compute.