You can buy a pair of DGX Sparks and run Deepseek V4 Flash at ~60-70TPS (once DSpark support matures over the next few days).

That will get you a near-frontier experience. DSv4 Flash launched in April with capabilities on par with GLM 5.0, which launched in February.

I really think giving it a year for the hardware market to come back to earth and spending a fraction of that for API access to the same models is a better use of the money.