Assuming you'll want to run a local llm, this is maybe the best directions? Local LLMs - OpenHands Docs

Thank you, yes, I am looking to run local LLMS and link them to my DGX Spark. But, I ran them through ollama and vLLM. With Ollama, the models ran slower and did not complete the task completely. With vLLM, models ran much faster; however, there were some errors with different models having different use cases. Is there a local model you can recommend, and how to run them, that will give me a way to do general tasks, coding tasks, and agentic workflows also? Or if you could give me different models to look into for the different plans I have, I would appreciate it.

On the DGX spark, I'm not sure the largest model you can serve, but if you can do minimax-m2.7 at 4 bit quant that might be a good one

Thank you for the help so far, i will let you know how it goes