I ran Gemma 4 31 B quantized so it fits in my RAM. The decoding speed was decent, but if you look at the newest models for example Gemini flash 3.5 they have a decoding speed of 280 token per second, they generate an entire page before my Mac locally generates a sentence.
Yes ofc I ran Gemma 4 for example, but compare that to the speed of Gemini in the cloud the difference is massive.
Local LLMs are cool but also pretty slow compared to cloud. If you have to wait half an hour for your Feature while coding you might still opt for the cloud agent.
Burning gas is so extremely bad that even throwing away your old ICE car and buying a new electric car is better than driving the ICE car until it „falls apart“. This was the research finding in Switzerland, but this result was so unwelcome that the research got hidden away. https://www.republik.ch/2025/06/11/amtliche-selbstzensur
I also hope that don’t get me wrong, but as I said: Waiting for the LLM agent to finish coding is currently a bottleneck in software development, they don’t pay high salaries for watching the AI code, they will prefer faster agents even if they are expensive, because they are not only paying the AI Company but also the software engineer overseeing them.