On: Llama.cpp supports Vulkan. why doesn't Ollama?

[Havoc]

ollama labels the qwen models R1, while the "R1" moniker standing on its own in deepseek world means the full model that has nothing to do with qwen.

https://ollama.com/library/deepseek-r1

That may have been ok if it was just same model at different sizes but they're completely different things here & it's created confusion out of thin air for absolutely no reason other than ollama being careless.

[dingocat → Havoc]

And their documentation makes that distinction clear, having dedicated a section specifically to the distilled models.