Qwen 3.8 27B Running for 63 hours on a RTX 3090 to solve the Riemann hypothesis

I let Qwen 3.8 27B 4bit quantized with 100K context window run autonomously for 63 hours (50 million+ tokens) to try to solve the RH. Of course it did not solve it, but the experiment still shows it's internal work, memory organization, strategies used and more. The interesting thing is that it never hallucinated an answer and never stopped trying new ideas to solve it. Multiple times it corrected it's own mistakes. I am really hopeful that one of the unsolved millenium prize problems will be solved by an agent or a swarm of agents powered by an open source model in the next 12 months. If you want to check out it's internal memories, code, strategies and more I published everything on HF: huggingface.co/datasets/gr0010/artificium-riemannhypothesis-experiment My next goal is to actually use an agent perhaps powered by a smarter open model like GLM 5.3 flash or a swarm of agents, to solve an open math problem. Please let me know if you tried something similar, what problem you'd suggest to tackle next, and if you have any question. If you have GPUs consider getting in touch with me, we could run multiple agents to create a swarm and get them to tackle a simple yet open math/coding problem.