Documentation & Guides

Everything you need to deploy, scale, and optimize your AI models on Nimbus.

Getting started

Install the CLI, deploy a HuggingFace model, and get your first inference endpoint live.

Deploy models programmatically with our Python SDK. Integrate into notebooks or CI/CD pipelines.

Bring your own Dockerfile for custom runtimes, dependencies, or model formats.

Complete command reference for deploying, scaling, monitoring, and debugging your deployments.

Text generation (LLaMA 2, Mistral)Deploy open-source LLMs with vLLM for optimized throughput

Image generation (Stable Diffusion)Serve SDXL models with automatic batching

Speech-to-text (Whisper)Real-time transcription with OpenAI Whisper

Embeddings (Sentence Transformers)High-throughput embedding generation for RAG

Computer vision (YOLO, SAM)Object detection and segmentation at scale

Fine-tuned modelsDeploy custom models trained on your data

Support

Start deploying models in minutes with our quickstart guide.