Modular

modular/max-nvidia-base

Modular

Lightweight MAX essentials. Faster downloads, minimal dependencies. Needs NVIDIA drivers.

modular/max-amd-base

Modular

AMD ROCm-optimized MAX for MI200/MI300 series. Fast GenAI inference on AMD hardware.

modular/max-amd

Modular

AMD ROCm-optimized MAX for MI200/MI300 series. Fast GenAI inference on AMD hardware.

modular/max-nvidia-full

Modular

Complete MAX stack: CUDA, PyTorch, cuDNN included. Production-ready NVIDIA GenAI deployment.

modular/max-cookbook

Modular

Full-stack recipes built upon MAX + FastAPI + React. Runs on AMD + NVIDIA.

modular/max-full

Modular

Universal MAX image supporting both NVIDIA & AMD GPUs. Cross-platform GenAI deployment solution.

modular/max-openai-api

Modular

Use Modular's MAX container image for your GPU-optimized generative AI deployment needs.

modular/max-openai-api-chart

Modular

Deploy GPU-optimized generative AI models using the MAX container Helm chart for Kubernetes.