Upload README.md with huggingface_hub

README.md

@@ -40,13 +40,16 @@ retrieves worse.
 
 | build | file | size (MB) | Mac ms* | backend takes | worst cosine vs eager | retrieval budget |
 |---|---|---|---|---|---|---|
-| fp32 | `embed_nomic_embed_text_v15_xnnpack_fp32.pte` | 547.2 | 45.5 | 64.5% | 1.000000 | 0% |
-| fp16 | `embed_nomic_embed_text_v15_xnnpack_fp16.pte` | 273.8 | 98.1 | 58.6% | 0.999999 | 7% |
-| Core ML (fp16, iOS) | `embed_nomic_embed_text_v15_coreml_all.pte` | 274.8 | 8.3 | 100.0% | 0.999793 | 46% |
-
-\*Mac arm64, median of 10, one 256-token sequence — a reference point for relative
-cost, not a device number. Torch eager fp32 on the same machine is
-45.2 ms.
+| fp32 | `embed_nomic_embed_text_v15_xnnpack_fp32.pte` | 547.2 | 45.1 | 64.5% | 1.000000 | 0% |
+| fp16 | `embed_nomic_embed_text_v15_xnnpack_fp16.pte` | 273.8 | 97.0 | 58.6% | 0.999999 | 7% |
+| Core ML (fp16, iOS) | `embed_nomic_embed_text_v15_coreml_all.pte` | 274.8 | 8.1 | 100.0% | 0.999793 | 46% |
+
+\*Mac arm64, one 256-token sequence, **fastest of five medians of ten** — a reference
+point for relative cost, not a device number. The host shares its cores with other work,
+and a single median does not survive that: the same eager model here measured 19.6 ms and
+182.8 ms twenty minutes apart. Contention only ever adds time, so the fastest repetition is
+the one that means something. Torch eager fp32, measured the same way, is
+44.9 ms.
 
 Cosine is measured against the model run in eager through its own pooling, over eight
 sentences. The last column is the one that decides: rank those eight against each