Eric Curtin<p>RamaLama just got multimodal! 🚀 See, understand & respond to visual info with new VLM capabilities. Shoutout to Xuan-Son Nguyen! <a href="https://social.treehouse.systems/tags/RamaLama" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RamaLama</span></a> <a href="https://social.treehouse.systems/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://social.treehouse.systems/tags/llamacpp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llamacpp</span></a></p><p><a href="https://developers.redhat.com/articles/2025/06/20/unleashing-multimodal-magic-ramalama" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">developers.redhat.com/articles</span><span class="invisible">/2025/06/20/unleashing-multimodal-magic-ramalama</span></a></p>
#Ramalama
0 posts0 participants0 posts today
Want to run #RamaLama AI on OpenShift DevSpaces Rohan Kumar has got you covered:
https://developers.redhat.com/articles/2025/06/13/how-run-ai-models-cloud-development-environments
Red Hat Developer · How to run AI models in cloud development environments | Red Hat DeveloperExplore using RamaLama to run private AI inference in cloud development environments and improve productivity. Follow this tutorial to get started
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.
GitHubGitHub - containers/ramalama: RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of ...
Local AI just got simpler!
Podman AI Lab now uses RamaLama’s GPU-ready containers—unifying efforts to streamline model deployment on your machine.
Faster setup
GPU acceleration
Consistent container experience
Learn more: https://developers.redhat.com/articles/2025/06/03/podman-ai-lab-and-ramalama-unite-easier-local-ai#
#AIDev #Podman #RamaLama #Containers #podmandesktop
Red Hat Developer · Podman AI Lab and RamaLama unite for easier local AI | Red Hat DeveloperLearn how Podman AI Lab and RamaLama work together to simplify local AI model execution, using containers and GPU support for faster, easier AI development
Lukáš Růžička si pro vás připravil článek o tom, jak na 
#Fedora používat #AI lokálně pomocí #ramalama.
https://mojefedora.cz/ramalama-aneb-vyhanime-lamy-na-vlastni-louku/
mojefedora.czRamalama aneb vyháníme lamy na vlastní louku | MojeFedora.cz
On route to #redhatsummit, watch out for: "AI inferencing for developers and administrators", "Securing AI workloads with RamaLama", "RamaLama Making developing AI Boring". We may even see a vlm demo, very accurate models as we can see here #ramalama #llamacpp
Build your own local RAG with Ramalama and granite model https://medium.com/@nicolabertoli92/build-your-own-local-rag-with-ramalama-and-granite-model-d5d89e612114
#Ramalama #aiml #rag
Medium · Build your own local RAG with Ramalama and granite model
Simplify AI data integration with RamaLama and RAG
https://developers.redhat.com/articles/2025/04/03/simplify-ai-data-integration-ramalama-and-rag#
#Docling #Ramalama #podman #aiml
How RamaLama helps make AI model testing safer https://www.infoworld.com/article/3853769/how-ramalama-helps-make-ai-model-testing-safer.html
#aiml #Ramalama #Container
@TheNewStack interviews Eric and Dan, maintainers of RamaLama about containerizing #AI development. If you haven't heard of the #RamaLama project before, this is a quick intro:
https://thenewstack.io/ramalama-project-brings-containers-and-ai-together/
The New Stack · RamaLama Project Brings Containers and AI TogetherProject founders Eric Curtin and Dan Walsh explain how RamaLama makes working with AI boring (aka easier) for developers by using OCI containers.
RAG does not prove as useful for helping out on the codebase with #LLM. At least not as good as I expected.
What does work for you? What model works best? Codelama? Deepseek? Mistral? Qwen?
Exciting news! https://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! 
ramalama.aiRamaLama
How RamaLama runs AI models in isolation by default
https://developers.redhat.com/articles/2025/02/20/how-ramalama-runs-ai-models-isolation-default
Red Hat Developer · How RamaLama runs AI models in isolation by default | Red Hat DeveloperDiscover how the RamaLama open source project can help isolate AI models for testing and experimenting
I find it baffling, how many people are outraged by this blogpost:
https://blogs.gnome.org/uraeus/2025/02/03/looking-ahead-at-2025-and-fedora-workstation-and-jobs-on-offer/
1. It's a personal blog, not even an official #Fedora / #RedHat blog ("official Red Hat communication happens on Redhat.com")
2. Yes, the blog post talks about AI. ABOUT #GRANITE AND #RAMALAMA, which are frameworks that allow setting up hw accelerated machine learning on Fedora #Workstation and make it easy. THIS DOESN'T MEAN WE'LL HAVE #CHATGPT IN FEDORA
Guys, reading comprehension is a thing...
blogs.gnome.orgLooking ahead at 2025 and Fedora Workstation and jobs on offer! | Christian F.K. Schaller
Meet llama-run, the newest tool in the llama.cpp ecosystem! Simplify running LLMs with one command, flexible configs, and seamless integration into OCI environments. Focus on outcomes, not infrastructure.
https://developers.redhat.com/blog/2024/12/17/simplifying-ai-ramalama-and-llama-run
Red Hat Developer · Simplifying AI with RamaLama and llama-run | Red Hat DeveloperIn our previous blog post, we introduced the RamaLama project, a bold initiative aimed at making AI development and deployment delightfully boring by leveraging the power of OCI containers. Since
Tired of the AI hype? 
I am too! 
RAMalama makes working with AI models boring (and that's a GOOD thing!).
Check out the latest #redhat #developers article to learn how RAMalama simplifies AI workflows:
- Streamline model deployment
- Reduce boilerplate code
- Focus on results, not infrastructure
#AI #MachineLearning #RAMalama
https://developers.redhat.com/articles/2024/11/22/how-ramalama-makes-working-ai-models-boring
Red Hat Developer · How RamaLama makes working with AI models boring | Red Hat DeveloperThe RamaLama project simplifies AI model management for developers by using OCI containers to automatically configure and run AI models.
The goal of #RamaLama is to make working with #AI boring.
https://github.com/containers/ramalama
#containers #sysadmin #tips
GitHubGitHub - containers/ramalama: RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of containers.RamaLama is an open-source developer tool that simplifies the local serving of AI models from any source and facilitates their use for inference in production, all through the familiar language of ...