Hunyuan Models — Hardware Requirements
5 Hunyuan models from Tencent and the community, from the smallest that runs in 0.6 GB of VRAM up to 80.4B parameters. Every row links to full quantization tables and GPU compatibility.
All Hunyuan Models by Size
| Model | Params | Runs from | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Hunyuan 0.5B Pretrain | 539M | 0.6 GB | 262K | ||
| Hunyuan 0.5B Instruct | 539M | 0.6 GB | 262K | ||
| HunyuanOCR | 1.1B | 0.7 GB | 131K | ||
| Hunyuan 7B Instruct | 7.5B | 2.6 GB | 33K | ||
| Hunyuan A13B Instruct | 80.4B | 22.7 GB | 33K |
Frequently Asked Questions
- How much VRAM do I need to run a Hunyuan model?
- The smallest Hunyuan model, Hunyuan 0.5B Pretrain, runs from 0.6 GB of VRAM at an aggressive quantization. Larger family members need proportionally more — see the table above for every model.
- Which Hunyuan models can I run on a 16 GB GPU?
- 4 of 5 Hunyuan models fit in 16 GB of VRAM at some quantization, including HunyuanOCR, Hunyuan 7B Instruct, Hunyuan 0.5B Pretrain.
- What is the most popular Hunyuan model to run locally?
- HunyuanOCR is the most downloaded Hunyuan model in local-friendly quantized formats. It runs from 0.7 GB of VRAM.