Refresh the card so its own manifest size line is current

Add the usage snippet, taken from the inference project's own README

Add the usage snippet, taken from the inference project's own README

Record the base-model link per build, as it differs between bf16 and quantized

Record the base-model link per build, as it differs between bf16 and quantized

Record the repo's sibling links in the manifest

Record the repo's sibling links in the manifest

Add split_model.json so the repo identifies its recipe

Restore bf16 weights (revert accidental test upload)

Upload MLX model via mlx-forge

Upload VOID model MLX (bf16)

initial commit