> Serving models is currently expensive. I'd argue that some big cloud providers...

		woadwarrior01 6 months ago \| parent \| context \| favorite \| on: Llama.cpp supports Vulkan. why doesn't Ollama? > Serving models is currently expensive. I'd argue that some big cloud providers have conspired to make egress bandwidth expensive. Cloudflare R2 has unlimited egress, and AFAIK, that's what ollama uses for hosting quantized model weights.