Hunyuan-A13B Instruct
Hunyuan-A13B Instruct has 80B total parameters and activates 13B per token. This post-trained release supports both fast responses and a longer reasoning mode.
Model design and access
The model uses fine-grained expert routing to reduce active computation. Tencent provides inference instructions for TensorRT-LLM, vLLM and SGLang. The full set of experts still determines weight storage. The pretrained and instruction-tuned checkpoints should remain separately identified.Hunyuan-A13B Instruct official model card
Practical use
Practical guidance. Compare both reasoning modes on the same workload. Longer thinking can change latency substantially, and the correct choice depends on whether the final answer improves.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| License | Tencent Hunyuan Community License; excludes the EU, UK and South KoreaHunyuan A13B community license |
| Context | 256K tokensHunyuan-A13B Instruct official model card |
| Attention | Grouped-query attentionHunyuan-A13B Instruct official model card |
Related models
Hy3 is a 295B mixture-of-experts language model with 21B active parameters and a separate 3.8B multi-token prediction layer.
Launch date not confirmedDownloadable · API- Hunyuan-A13B Pretrain
Tencent · Hunyuan-A13B
A pretrained mixture-of-experts language model with 80B total and 13B active parameters.
Launch date not confirmedDownloadable