I did a little experiment. I asked ChatGPT 4o (in the cloud) and the Llama 3.1 70b model (locally via Ollama), the same question: "What verse changes did Schiller make for Beethoven's 9th symphony?". Both models got the right answer, in fairness GPT 4.o did it much faster and had a much more elaborate answer than Llama3.1 70b that took a good 2 minutes (running on my desktop PC!). But in the end, I liked the answer from Llama 3.1 better because it was concise, to the point, minimalistic (as you would expect from a 70b model) and in a way more helpful. If you want to follow the the experiment in real-time, I've recorded it for just that purpose. This is also the reason why this is a blog post and not just an update, because I can upload more than one video file. ChatGPT 4o: Llama 3.1 (70b) via Ollama (jump to 50 seconds, it takes a while to load the model): What do you think?