How can it be this good running on your own computer
Discussion
You can run it with multiple or a single GPU, and even with just a CPU.
The lower the compute power, the smaller the model, and the worse the result.
If you want similarish results, you need a lot of compute.
The difference in the training of this model is that is uses a smaller but higher quality testing data set. For example, they include chatgpt conversations in the training data. You can use a more powerful model to train a smaller imitating model.
I've been running LLaMA on my laptop and even my phone recently and it's very very good. The open source LLMs are developing even more exponentially than the proprietary ones.