Artifacts

Converts a Hugging Face model to a quantized GGUF file and uploads it to your account; needs login.

Pick a GPU and a model to see whether it fits in memory for inference or training.

Calculates the memory a Hugging Face Hub model needs at different precisions for inference and training.

Estimates how much GPU memory a language model needs for a given size, quantisation and context length.

Converts PyTorch model weights to the safetensors format; asks for a Hugging Face token.

Edit a Jinja chat template and preview how it formats a conversation into model input text.

Load and run GGUF language models directly in your browser without a server.

Converts a Hugging Face model to Apple MLX format and uploads it to your account; needs login.

Predicts training memory use for a transformer from pasted config or manual architecture values.

Calculates VRAM needs for a GGUF model, including splitting layers across GPU and CPU.

Computes memory for a GGUF model from GPU layers and context size.

Exports a Hugging Face model to ONNX and opens a pull request with the result; needs login.

Fetches a GitHub repository and merges its files into one text file for pasting into an LLM.

Counts the number of tokens a piece of text uses with the Llama tokenizer.

Draws and exports masks to use in inpainting workflows.

Web calculator for estimating and comparing LLM API costs across models.

Classic Tesseract OCR: upload an image and get the recognized text.

Open-source AI note-taker that produces notes from your sources and cites where each point comes from.

Checks whether an image looks AI-generated or synthetic, free and without sign-up.

Runs a fruit fly simulation in your browser using WebGPU.

Combines a left-eye and a right-eye image pair into a red-cyan 3D anaglyph picture.

Rearranges and remixes a song's beats with effects, driven by beat detection.

Upload a file and receive Markdown generated with Microsoft's MarkItDown library.

Multilingual text-to-speech that runs on-device in the browser using the Supertonic 3 voice model.