While everyone's talking about Apple's Containerization framework announcement at WWDC, just a few days ago #krunkit quietly hit a major milestone: GPU passthrough in VMs, with up to 80% native LLM performance.

#krunkit and #podman are still the best hypervisor and container combination on macOS. #libkrun is also a great option for AI microVMs. We are thankful to be able to take advantage of these features in #RamaLama #AI

https://github.com/containers/ramalama

But I'm still looking forward to where Apple's variants go.

https://developers.redhat.com/articles/2025/06/05/how-we-improved-ai-inference-macos-podman-containers

I've heard a couple of people echo this and I agree! AI is a tool, it's important to use available tools

https://www.breakingnews.ie/ireland/workers-who-use-ai-will-replace-workers-who-dont-td-on-positives-of-artificial-intelligence-1735133.html

Here's an example of an AI bot, helping me review a PR from yesterday:

https://github.com/ericcurtin/linenoise.cpp/pull/7#discussion_r1976225575

🚀 Exciting news! ramalama.ai is officially live! 🎉

RamaLama makes AI inferencing boring. Just OCI containers handling AI models seamlessly.

Huge thanks to Jessica Chitas & Cara Delia for making this happen! 🙌

#AI #ML #RamaLama

Ollama much?? Try Ramalama

https://www.linkedin.com/pulse/ollama-much-try-ramalama-surya-rekha-tw5kf/?trackingId=I0KmMXGUMVKgJQPXfeDImw%3D%3D

🚀 Excited for #FOSDEM! Don’t miss "RamaLama: Making working with AI Models Boring". Pierre-Yves Chibon and I will also be talking about "Bootable Containers & Image Mode". Let’s explore the future of AI and OS innovation together! 🌟 #AI #RamaLama #bootc