Update README.md

README.md

@@ -47,3 +47,10 @@ We provide some qualitative comparison between FastHunyuan 6 step inference v.s.
 | ![FastHunyuan 6 step](assets/distilled/3.gif) | ![Hunyuan 6 step](assets/undistilled/3.gif) |
 | ![FastHunyuan 6 step](assets/distilled/4.gif) | ![Hunyuan 6 step](assets/undistilled/4.gif) |
 
+## Memory requirements
+
+For inference, we can inference FastHunyuan on single RTX4090. We now support NF4 and LLM-INT8 quantized inference using BitsAndBytes for FastHunyuan. With NF4 quantization, inference can be performed on a single RTX 4090 GPU, requiring just 20GB of VRAM.
+
+For Lora Finetune, minimum hardware requirement
+- 40 GB GPU memory each for 2 GPUs with lora
+- 30 GB GPU memory each for 2 GPUs with CPU offload and lora.