Directory

Amazon's public cloud with hundreds of usage-billed services spanning compute (EC2, Lambda), storage (S3), databases (RDS), networking, AI (Bedrock) and analytics

Apple's on-device machine-learning runtime for iOS and macOS apps, with the open-source coremltools package for converting PyTorch and other models to its format

Open-source software that pools several Apple Silicon Macs (and Linux hosts) into one local inference cluster, sharding large models across devices with MLX

Google's public cloud with Compute Engine, GKE, Cloud Run, BigQuery, Cloud Storage and the Vertex AI platform for Gemini and other models

Low-latency hosted inference API for open-weight models on Groq's LPU hardware, OpenAI-compatible, with speech-to-text, text-to-speech, tool use and batch tiers

Microsoft's public cloud with virtual machines, AKS, Azure Functions, Cosmos DB, Azure Database for PostgreSQL, Entra ID identity and Microsoft Foundry for hosted AI models

Cloud platform for open-source models: serverless and dedicated inference, fine-tuning, GPU clusters, batch jobs and code sandboxes behind an OpenAI-compatible API