TencentHunyuan dense
Hunyuan 0.5B Instruct
Hunyuan 0.5B Instruct is the smallest size in Tencent’s dense language-model series. It is tuned to follow instructions and supports fast and deliberate reasoning modes.
Model design and access
The family uses training strategies related to Hunyuan-A13B. Its 0.5B size is a dense parameter count, not the active count of a larger expert network. Official quantized formats reduce storage needs but remain variants of this checkpoint.Hunyuan 0.5B Instruct official model card
Practical use
Practical guidance. Evaluate short structured tasks at the precision and context length that you intend to serve. Long inputs can make cache memory significant even for a small model.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| License | Tencent Hunyuan Community License; excludes the EU, UK and South KoreaHunyuan dense model community license |
| Architecture | Dense transformer with grouped-query attentionHunyuan 0.5B Instruct official model card |
| Context | 256K tokensHunyuan 0.5B Instruct official model card |
Related models
- Hunyuan 0.5B Pretrain
Tencent · Hunyuan dense
A 0.5B dense pretrained language model with a 256K context for further adaptation.
Launch date not confirmedDownloadable