Realistically, the biggest models you can run at a reasonable price right now are quantized versions of things like the Qwen3 30B A3B family. A 4-bit quantized version fits in roughly 15GB of RAM. This will run very nicely on something like an Nvidia 3090. But you can also use your regular RAM (though it will be slower).
These models aren't competitive with GPT 5 or Opus 4.5! But they're mostly all noticeably better than GPT-4o, some by quite a bit. Some of the 30B models will run as basic agentic coders.
There are also some great 4B to 8B models from various organizations that will fit on smaller systems. A 8B model, for example, can be a great translator.
(If you have a bunch of money and patience, you can also run something like GPT OSS 120B or GLM 4.5 Air locally.)
Don't need patience for these, just money. A single RTX 6000 Pro runs those great and super fast.
Runs everything today with bleeding edge performance.
Overall whats the difference between 8k or 30k?
/s
As long as you have the money this hardware is easily accessible to normal people, unlike fancy server hardware.
This one runs at perfectly servicable pace locally on a laptop 5090 with 64gb system ram with zero effort required. Just download ollama and select this model from the drop-down.
OpenRouter gives you $10 credit when you sign up - stick your API key in and compare as many models as you want. It's all browser local storage.