CallMeEich
/

ltx-2.3-mlx-q4

Model card Files Files and versions

ltx-2.3-mlx-q4 / quantize_config.json

CallMeEich's picture

Upload MLX model via mlx-forge

daaab1c verified 6 months ago

Raw History Blame Contribute Delete

100 Bytes

{
  "quantization": {
    "bits": 4,
    "group_size": 64,
    "only_transformer_blocks": true
  }
}