Sprint 2: a validator that scores corruption, and one prompt on two backends

Sprint 2 (planned 23 November to 6 December 2026, started early on 9 November) had two measurable goals: the glyphsift validator's score falls steadily as synthetic OCR noise rises, and the same prompt is answered on WebGPU and on WebAssembly. Both were met. Every figure below names the command that produced it and the saved output it was copied from.

Any figure that lands here was measured on an Apple-silicon development machine and is a placeholder; the reference 8 GB Windows laptop without a GPU has not been measured yet.

Correction, 14 November 2026. The "What is next" section below says Sprint 3 is the runtime alpha, including the WebLLM backend. The WebLLM backend moved to Sprint 4; Sprint 3 delivered the runtime alpha without it, and WebLLM was then cut from Sprint 4 (TD-08, not yet). The score-versus-noise figures below are the Sprint 2 ones; glyphsift's docs/score-vs-noise.csv was regenerated in Sprint 3 after two rule changes, so the file in the repository no longer reproduces this table. The benchmarks page carries the regenerated figures. The text below is otherwise left as it was written.

The done-when, stated honestly

Same prompt answered on WebGPU and on WebAssembly with the test model SmolLM2-135M-Instruct (q4), in Chrome on an Apple-silicon Mac only. This is not the Hindi production model; Windows and the 8 GB no-GPU laptop are not measured.

glyphsift: score versus noise

Command: cargo run -p glyphsift-cli --release -- bench --corpus bench/corpus/clean.txt --seeds 1,2,3 --csv docs/score-vs-noise.csv --svg docs/score-vs-noise.svg (output in docs/score-vs-noise.csv in the glyphsift repository and evidence/sprint-2/D3/bench-run-1.log).

Noise level pMixed-family mean score (ppm, seeds 1 to 3)
01,000,000
0.01998,454
0.02996,931
0.05991,588
0.1983,739
0.2967,065
0.4932,405

runtime: one prompt, two backends

Command: RUNTIME_MODEL=1 RUNTIME_REQUIRE_WEBGPU=1 npm run test:model (output in evidence/sprint-2/D1/model-run.json), prompt "What is the capital of France? Answer in one word.", greedy decoding.

LegLoadPrefillDecodeSpeedAnswer
WebGPU2,667 ms66 ms51 ms155.9 tokens per secondThe capital of France is Paris.
WebAssembly2,592 ms368 ms732 ms10.9 tokens per secondThe capital of France is Paris.

The model decision

Planned production model: Qwen3-1.7B (Apache-2.0), WebGPU q4f16 1.43 GB, WASM q8 1.74 GB. Provisional until the Sprint 5 measurement on an 8 GB laptop; contingency Qwen3-0.6B.

The comparison table, the licence conditions and the Hindi evidence for each candidate are in the runtime repository's docs/model-choice.md. Loaded once in a browser: a local, unscored WebGPU smoke run of five synthetic Hindi prompts on an Apple-silicon Mac, which needed ONNX Runtime graph optimisation turned off (evidence/sprint-2/D1/hindi-smoke.json). The decision stays provisional.

What else landed

What did not pass

What is next

Sprint 3 is the runtime alpha, including the WebLLM backend. Sprint 5 is the measurement on the 8 GB Windows laptop and the real Hindi pipeline in dockit. Until then every figure on this site stays labelled as a placeholder.

Prose on this page is CC BY 4.0; attribute "Airplane Mode Labs" with a link.