[Scaevolus]

It's not that it's reserving power, but rather that you hit some bottleneck on a 3070 Ti before running into thermal limits-- it's likely limited by either tensor core saturation or RAM throughput. Running the workload with Nvidia's profiling tools should make the bottleneck obvious.

[lambda]

Generally the bottleneck is RAM throughput. Inference, in particular token generation, especially on a single user instance, is not all that computationally complex; you're doing some fairly simple calculations for each parameter, the time is dominated by just transferring each parameter from RAM to the cores. A 31B dense model like Gemma 4 has to transfer 31B parameters (at 16 bits per parameter for the full model, though on consumer hardware people generally run 4-8 bit quantizations) from RAM to the cores, that's a lot of memory transfer.

Prompt processing or parallel token generation can do a bit more work per memory transfer, as you can use the same weights for a few different calculations in parallel. But even still, memory bandwidth is a huge factor.