Step through an illustrative next-token path
Click a token chip or press Step through to follow a single token through every stage. Token segments, scores, and percentages are illustrative; this page does not load model weights or a model tokenizer.
Paste a Hugging Face link (repo or config.json URL). Dimensions, attention variant, MoE layout and quantization are read straight from the config.
Click a token chip or press Step through to follow a single token through every stage. Token segments, scores, and percentages are illustrative; this page does not load model weights or a model tokenizer.
Every weight in a model is stored in a numeric format. Fewer bits usually means less weight memory; speed depends on hardware and kernels, while quality depends on the quantization method. Select a format to see the trade-offs below.
64 illustrative weights, snapped to the selected format's grid. Gray dots are the originals; purple dots are the stored approximations.
Weight memory only (KV cache and activations come on top). The top option sizes whatever model you're exploring — paste a config.json to size any model. MoE bars use total weights, not the active subset.