# Hunyuan-A13B Technical Report > Source: > Published: 2026-09-24 02:30:06+00:00 We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains 80 billion total parameters but activates only 13 billion during inference, balancing model capability, computational efficiency, and deployment cost. The model is pretrained on a rig