Model Hubs

Curated foundation models served via OpenAI-compatible APIs and managed endpoints on Databricks.

AI art platform hosting diffusion checkpoints and LoRAs with online generation.

Optimized Intel OpenVINO reference models and demos for high-performance inference.

Fast inference and fine-tuning for 200+ open models with a unified developer experience.

Optimized model catalog for NVIDIA GPUs—LLMs, vision, speech—with containers and inference recipes.

Aggregator listing pretrained models and code across frameworks and tasks.

Repository of reusable ML modules and models for TensorFlow with ready-to-use examples.

Desktop app to discover, download, and run local LLMs (MLX/llama.cpp) from various hubs.

Official PyTorch repository of pretrained models across vision, NLP, and audio for easy loading.

Community ONNX models and links (now transitioning many artifacts to Hugging Face).