RELEASE · MODELS · #927
Hunyuan-A13B: open-source 80B Mixture-of-Experts LLM activating 13B
An arXiv paper (arXiv:2609.27284v1) introduces Hunyuan-A13B, an open-source Mixture-of-Experts large language model with 80 billion total parameters that activates 13 billion during inference. It was pretrained on a filtered 20T-token corpus with enhanced STEM curation, uses supervised fine-tuning and large-scale reinforcement learning, adds a dual-mode Chain-of-Thought mechanism for fast vs. slow reasoning, and reports competitive results across math, science, programming and agent tasks with high inference throughput.
KEY POINTS
- An arXiv paper (arXiv:2609.27284v1) introduces Hunyuan-A13B, an open-source Mixture-of-Experts large language model with 80 billion total parameters that activates 13 billion during inference.
- It was pretrained on a filtered 20T-token corpus with enhanced STEM curation, uses supervised fine-tuning and large-scale reinforcement learning, adds a dual-mode Chain-of-Thought mechanism for fast vs.
- slow reasoning, and reports competitive results across math, science, programming and agent tasks with high inference throughput.
WHY IT MATTERS
An open-source 80B MoE that activates only 13B at inference and combines dataset curation, RL, and adaptive reasoning could materially lower cost/latency trade-offs while enabling broader research and deployment of capable LLMs.