I can run 7B models on my laptop with its embedded GPU. Running on a phone or a Pi is possible with smaller models, but very slow. Expect good speed with a desktop Nvidea GPU. Later this year, there should be new computers with an NPU integrated to the CPU which should speed up computers that don’t have a dedicated GPU. (But a GPU will still outperform them by a lot.)
70B models will run very slowly on even the best consumer hardware due to memory limitations.
If someone is paying you to write code, they have some say in the contract about how it is licensed. You could be upfront about only doing GPL, and they could be upfront about saying no. But if you try to do it after the fact, that’s a violation of the contract.