Optimize max peak memory usage and add warnings on mobile for higher models

tests/models.test.ts

@@ -5,6 +5,7 @@ import {
   WHISPER_LANGUAGES,
   estimateDefaultDownloadBytes,
   estimateDownloadBytes,
+  estimatePeakLoadBytes,
   formatModelSize,
   getFasterWhisperModel,
   getModel,
@@ -163,6 +164,38 @@ describe("size estimates", () => {
   });
 });
 
+describe("estimatePeakLoadBytes (D-027)", () => {
+  const medium = getModel("onnx-community/whisper-medium-ONNX")!;
+  const turbo = getModel("onnx-community/whisper-large-v3-turbo")!;
+
+  test("is ~2x the larger of the two weight files, not their sum", () => {
+    const dtype = resolveDefaultDtype(medium.id, "wasm"); // q4
+    const peak = estimatePeakLoadBytes(medium, dtype);
+    const download = estimateDownloadBytes(medium, dtype);
+    // The combined download sums both files; the peak only doubles the
+    // larger one — smaller than 2x the sum, but bigger than the sum alone
+    // once the sequential-load patch keeps only one file resident at a time.
+    expect(peak).toBeLessThan(2 * download);
+    expect(peak).toBeGreaterThan(download);
+  });
+
+  test("mixed per-part dtypes (fp16 encoder + q4 decoder) peak on the larger encoder", () => {
+    const dtype = resolveDefaultDtype(turbo.id, "webgpu"); // fp16 encoder, q4 decoder
+    const peak = estimatePeakLoadBytes(turbo, dtype);
+    // large-v3-turbo's encoder (635M) dwarfs its decoder (174M) even before
+    // fp16 vs q4 is factored in, so the encoder alone should set the peak.
+    const encoderOnlyPeak = 2 * turbo.encoderParamsM * 1e6 * 2; // fp16 = 2 bytes/param
+    expect(peak).toBeCloseTo(encoderOnlyPeak, -5);
+  });
+
+  test("scales up with a larger model at the same dtype", () => {
+    const tiny = getModel("onnx-community/whisper-tiny.en")!;
+    expect(estimatePeakLoadBytes(medium, "q4")).toBeGreaterThan(
+      estimatePeakLoadBytes(tiny, "q4"),
+    );
+  });
+});
+
 describe("WHISPER_LANGUAGES", () => {
   test("codes are unique, lowercase, and include common languages", () => {
     const codes = WHISPER_LANGUAGES.map((entry) => entry.code);