Your options are to run smaller models or wait. llama3.2:3b fits on my 1080 Ti VRAM and is sufficiently fast. Bigger models will get split between VRAM and RAM and run slower but it’ll work.

Not all models are Gen AI style LLMs. I run GPU based speech to text models on my GPU too for my smart home.

It has to be the employees not the state because companies withhold it and remit directly to the IRS. Not saying you should do this, but if you increase your withholdings exemptions then it won’t go to the IRS. Though you will owe it in April and may have to pay penalties for underwitholding.