Categories

Text-generation and instruction-tuned models — GGUF, safetensors, and full-precision weights.

Diffusion and flow-matching models for text-to-image and image editing.

Speech recognition, text-to-speech, and audio generation models.

Vision-language and any-to-any models.

Text and multimodal embedding models for retrieval and search.

Everything else — datasets adjacent to weights, tokenizers, adapters.