Even with 10x more efficient models and GPU compute, hundreds of GB of VRAM will still be on the order of tens of thousands of USD for the foreseeable future.
Beyond that, running inference on the equivalent of a 2025 SOTA model with 100GB of VRAM is very unlikely. One consistent quality of transformer models has been the fact that smaller and quantized models are fundamentally unreliable, even though high quality training data and RL can boost the floor of their capabilities.