quantized duplicated precisions.json, which is authoritative for the
quantized/non-quantized partition. default expressed a per-repository
recommendation nothing consumed: the library resolves its own per-platform
default. Both are gone from the schema.
Adds library_name to the model card, and pipeline_tag where it was missing.
Brings the config and card licenses into agreement, and repairs the variant
declarations that did not match the files actually published here.
MLX exports well (3 subgraphs) but fails at execute on device, and is 57% larger than the XNNPACK build that runs in 1.5 ms. Core ML fails with error 0x1 under CPU_AND_NE; CPU_ONLY works but has no advantage over XNNPACK.
