Hunyuan A13B Instruct

Hunyuan A13B Instruct is an open-weight, instruction-tuned large language model from Tencent's Hunyuan team, using a Mixture-of-Experts architecture with 80B total parameters and 13B active at inference. It supports a 256K-token context window and is optimized for reasoning, math, long-document analysis, and agentic tool-use workflows. Source: supabase.