wasmicro

Tiny transformer inference for the web. One file. No build step.

WASM module

Statusloading…
Version
Bundle size
Cold load time

Matmul benchmark

Runs n × n matrix multiplication inside WASM.

(click Run)

Semantic search

Drop in model.safetensors and vocab.txt, then rank documents by embedding similarity.

(no model loaded)

Default config: all-MiniLM-L6-v2 (hidden=384, layers=6, heads=12).