Sure if you have a specific need you can specialize some NN with the right architecture, collecting the data, doing the training several times, testing the performances, ... Or: you can download an already built LLM and write a prompt.
So one of the use cases we're serving in production is predicting energy consumption for a home. Whilst I've not tried, I'm very confident that providing an LLM the historical consumption and asking it to predict future consumption will under perform compared to our forecasting model. The compute required is also several orders of magnitude lower compared to an LLM
Nope, gemma3 and qwen3 exist of many sizes, including very small ones, that 4-bit quantized can run on very small systems. Qwen3-0.6B, 1.7B, ... imagine if you quantize those to 4 bit. But there is the space for the KV cache, if we don't want to limit the runs to very small prompts.
