@ninjadodo Sounds like I should check it out.

@pafurijaz So far, this is the best model I have used for Blender python coding. So thank you!!!

@pafurijaz Thanks. Fortunately I was forced to upgrade my computer and video card, as Unreal Engine is a VRAM pig. Builder insisted I future-proof my machine with a 3090, as it won't break the bank like the 4000 series, but this gave me my current availability of 24GB of VRAM. It was trying to split to the "Shared GPU" memory, but (I think) setting Ollama with graphic performance priority fixed it so now all 21GB in VRAM (or it was because had more apps closed?).

@ninjadodo In retrospect, it was a silly question... so thanks or the nudge. Will have to migrate. gamedev makes sense considering my interest & profession. Hmm... 😜

@pafurijaz Amen. Coincidentally, I was referencing Azimov in my conversations on how excited I was about LLMs that can run locally. I actually picture his works whenever I dream of such things.

@pafurijaz Been looking for a model for exactly this purpose. Will check it out. (this one? https://ollama.com/library/qwen2.5-coder:32b)

@chengdulittlea I like.