Hunyuan 4B Instruct
Hunyuan 4B Instruct is the intermediate 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 4B 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 4B Instruct official model card
Practical use
Practical guidance. Evaluate longer instructions with several conditions 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 4B Instruct official model card |
| Context | 256K tokensHunyuan 4B Instruct official model card |
Related models
- Hunyuan 4B Pretrain
Tencent · Hunyuan dense
A 4B dense pretrained language model with a 256K context for further adaptation.
Launch date not confirmedDownloadable