Uploaded November 2025 | Updated September 2026, 1 week ago
In this episode of Docker’s AI Guide to the Galaxy, Oleg Šelajev talks with Eric Curtin from the Docker Model Runner team about the latest innovations that make it easier than ever to run and host AI models locally.
They explore how Docker Model Runner is evolving to support new inference engines, expanded GPU acceleration, and multimodal AI, all while keeping the familiar Docker simplicity developers love.
🚀 What’s new in this episode:
🧠 Multi-engine support – Run models using Llama.cpp or vLLM for flexibility and performance
⚙️ Expanded GPU acceleration – Vulkan and AMD support bring AI to nearly any hardware setup, even integrated GPUs
📦 OCI model packaging – Push and pull AI models through Docker Hub, GHCR, or private registries
💬 Enhanced CLI UX – Smarter, more responsive command-line experience with context retention and cancellation options
🖼️ Multimodal AI demos – Run models that can see and understand images directly on your local machine
☁️ Docker Offload – Tap into NVIDIA GPUs in the cloud while keeping your seamless local workflow
From fine-tuning small models to deploying multimodal apps at the edge, Docker Model Runner brings AI anywhere: simple, secure, and open source.
🎧 Watch now to see the latest features in action and learn how Docker is redefining how developers build, run, and scale AI workloads.
🔥 Want More Docker Content?
If you found this demo exciting, hit that like button and subscribe for more! We’ve got even more Docker demos coming your way in this ongoing series showcasing new tools, integrations, and powerful workflows to level up your projects. Stay tuned!
Where to find Docker:
Docker: docker.com
LinkedIn: linkedin.com/company/docker
Bluesky: https://bsky.app/profile/docker.com
X: @docker
Instagram: @dockerinc
#Docker #AI #ModelRunner #OpenSource #LLM #VLLM #LlamaCPP #Vulkan #EdgeAI #Containers #MachineLearning #ArtificialIntelligence #HuggingFace #DockerAI
In this episode of Docker’s AI Guide to the Galaxy, Oleg Šelajev talks with Eric Curtin from the Docker Model Runner team about the latest innovations that make it easier than ever to run and host AI models locally.
They explore how Docker Model Runner is evolving to support new inference engines, expanded GPU acceleration, and multimodal AI, all while keeping the familiar Docker simplicity developers love.
🚀 What’s new in this episode:
🧠 Multi-engine support – Run models using Llama.cpp or vLLM for flexibility and performance
⚙️ Expanded GPU acceleration – Vulkan and AMD support bring AI to nearly any hardware setup, even integrated GPUs
📦 OCI model packaging – Push and pull AI models through Docker Hub, GHCR, or private registries
💬 Enhanced CLI UX – Smarter, more responsive command-line experience with context retention and cancellation options
🖼️ Multimodal AI demos – Run models that can see and understand images directly on your local machine
☁️ Docker Offload – Tap into NVIDIA GPUs in the cloud while keeping your seamless local workflow
From fine-tuning small models to deploying multimodal apps at the edge, Docker Model Runner brings AI anywhere: simple, secure, and open source.
🎧 Watch now to see the latest features in action and learn how Docker is redefining how developers build, run, and scale AI workloads.
🔥 Want More Docker Content?
If you found this demo exciting, hit that like button and subscribe for more! We’ve got even more Docker demos coming your way in this ongoing series showcasing new tools, integrations, and powerful workflows to level up your projects. Stay tuned!
Where to find Docker:
Docker: docker.com
LinkedIn: linkedin.com/company/docker
Bluesky: https://bsky.app/profile/docker.com
X: @docker
Instagram: @dockerinc
#Docker #AI #ModelRunner #OpenSource #LLM #VLLM #LlamaCPP #Vulkan #EdgeAI #Containers #MachineLearning #ArtificialIntelligence #HuggingFace #DockerAI
