llamers.

Watch a language model
actually think.

llamers is a complete, from-scratch transformer — tokenizer, attention, RoPE, KV cache, sampling, even training — running live in pure JavaScript. No mocks, no magic. Open the hood and watch every token take shape.

Open the playground → Start learning

See the attention

Per-head heatmaps update as each token is generated.

Watch the cache grow

The KV cache fills one position at a time — exactly as in real runtimes.

Train it yourself

Real backpropagation in the browser. Watch the loss fall, then generate.