Hunyuan-A13B Technical Report
arXiv:2609.27284v1 Announce Type: new Abstract: 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…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-09-24 04:00 · arXiv cs.AI
Hunyuan-A13B Technical Report