GgufQuantOption

One downloadable quantization of a GGUF repository.

gguf_fileGguf File (string)required

Repo-relative first shard of the quant's group; pin this to download it.

labelLabel (string)required

Human quant label, e.g. Q4_K_M or UD-Q2_K_XL.

total_bytesTotal Bytes (integer)required

Exact total bytes of the quant's shard group.

shard_countShard Count (integer)required

Number of GGUF shards in the group.

GgufQuantOption

{
  "gguf_file": "string",
  "label": "string",
  "total_bytes": 0,
  "shard_count": 0
}