Aller au contenu
ModelVérifiéExterne
Télécharger

Ernie Image Turbo Mlx Q8

Int8 quantization (groupsize 64, attention and FFN Linear weights only, leaving the small projections and the VAE in bf16) of dgrauet/ernie-image-turbo-mlx, the MLX conversion of baidu/ERNIE-Image-Turbo.

Sourcehuggingface.co/dgrauet/ernie-image-turbo-mlx-q8/tree/0cf221141d1f356ab52938e4a16fb8aaca761f4f
TypeText modelModèle de basebaidu/ERNIE-Image-TurboVersiontext_encoderÉditeur@dgrauetCClasse

Source du modèle

Type
Text model
Taille du fichier
3,39 GB
Modèle de base
baidu/ERNIE-Image-Turbo
Version
vtext_encoder
Mis à jour
2 oct. 2026
Éditeur
@dgrauet
Téléchargements
0
Source
Hugging Face

Description de la source

dgrauet/ernie-image-turbo-mlx-q8

Int8 quantization (group_size 64, attention and FFN Linear weights only, leaving the small projections and the VAE in bf16) of dgrauet/ernie-image-turbo-mlx, the MLX conversion of baidu/ERNIE-Image-Turbo.

Quantized with mlx-forge (mlx-forge convert ernie-image --variant turbo --quantize --bits 8).

Usage

These weights can be used with ernie-image-mlx:

pip install ernie-image-mlx
ernie-image-mlx generate \
    -p "一只黑白相间的中华田园犬" \
    --repo-id dgrauet/ernie-image-turbo-mlx-q8 \
    -o dog.png

Keep quantize_config.json next to the weights (the loader also infers bits/group_size from the weight shapes if it is missing).

Related Projects

Files

  • model_index.json (547.00 B)
  • pe_tokenizer_tokenizer_config.json (20.63 KB)
  • quantize_config.json (107.00 B)
  • scheduler_scheduler_config.json (482.00 B)
  • special_tokens_map.json (414.00 B)
  • split_model.json (1.08 KB)
  • text_encoder.safetensors (3.39 GB)
  • text_encoder_config.json (1.64 KB)
  • tokenizer.json (8.83 MB)
  • tokenizer_tokenizer_config.json (379.00 B)
  • transformer.safetensors (8.11 GB)
  • transformer_config.json (422.00 B)
  • vae.safetensors (160.33 MB)
  • vae_config.json (836.00 B)

Sources

1 source
Hugging FacePrincipalVersion 0cf221141d1f356ab52938e4a16fb8aaca761f4f
huggingface.co/dgrauet/ernie-image-turbo-mlx-q8/tree/0cf221141d1f356ab52938e4a16fb8aaca761f4f

Vérifié 2 oct.

Artefacts du modèle

1 artefact

text_encoder.safetensors

safetensors · 3,39 GB · SHA-256 15efee9b9182…12d5 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme2 oct.huggingface.co/dgrauet/ernie-image-turbo-mlx-q8

--- library_name: mlx license: apache-2.0 base_model: baidu/ERNIE-Image-Turbo tags: - mlx - mlx-forge - apple-silicon - safetensors - quantized - int8 --- # dgrauet/ernie-image-turbo-mlx-q8 Int8 quantization (group_size 64, attention and FFN Linear weights only, leaving the small projections and the VAE in bf16) of [dgrauet/ernie-image-turbo-mlx](https://huggingface.co/dgrauet/ernie-image-turbo-mlx), the MLX conversion of [baidu/ERNIE-Image-Turbo](https://huggingface.co/baidu/ERNIE-Image-Turbo). Quantized with [mlx-forge](https://github.com/dgrauet/mlx-forge) (`mlx-forge convert ernie-image --variant turbo --quantize --bits 8`). ## Usage These weights can be used with [ernie-image-mlx](https://github.com/dgrauet/ernie-image-mlx): ```bash pip install ernie-image-mlx ernie-image-mlx generate \ -p "一只黑白相间的中华田园犬" \ --repo-id dgrauet/ernie-image-turbo-mlx-q8 \ -o dog.png ``` Keep `quantize_config.json` next to the weights (the loader also infers bits/group_size from the weight shapes if it is missing). ## Related Projects - **mlx-forge (conversion):** https://github.com/dgrauet/mlx-forge - **mlx-arsenal (reusable MLX ops):** https://github.com/dgrauet/mlx-arsenal - **mlx-porting (Claude Code skill):** https://github.com/dgrauet/claude-skill-mlx-porting - **bf16 variant:** https://huggingface.co/dgrauet/ernie-image-turbo-mlx - **q4 variant:** https://huggingface.co/dgrauet/ernie-image-turbo-mlx-q4 ## Files - `model_index.json` (547.00 B) - `pe_tokenizer_tokenizer_config.json` (20.63 KB) - `quantize_config.json` (107.00 B) - `scheduler_scheduler_config.json` (482.00 B) - `special_tokens_map.json` (414.00 B) - `split_model.json` (1.08 KB) - `text_encoder.safetensors` (3.39 GB) - `text_encoder_config.json` (1.64 KB) - `tokenizer.json` (8.83 MB) - `tokenizer_tokenizer_config.json` (379.00 B) - `transformer.safetensors` (8.11 GB) - `transformer_config.json` (422.00 B) - `vae.safetensors` (160.33 MB) - `vae_config.json` (836.00 B)

Readme11 juil.huggingface.co/dgrauet/ernie-image-turbo-mlx-q8

--- library_name: mlx license: apache-2.0 base_model: baidu/ERNIE-Image-Turbo tags: - mlx - mlx-forge - apple-silicon - safetensors --- # dgrauet/ernie-image-turbo-mlx-q8 MLX format conversion of [baidu/ERNIE-Image-Turbo](https://huggingface.co/baidu/ERNIE-Image-Turbo). Converted with [mlx-forge](https://github.com/dgrauet/mlx-forge). - **Quantization:** int8 ## Usage These weights can be used with [ernie-image-mlx](https://github.com/dgrauet/ernie-image-mlx). ```bash pip install ernie-image-mlx ernie-image-mlx generate \ -p "一只黑白相间的中华田园犬" \ --repo-id dgrauet/ernie-image-turbo-mlx-q8 \ -o dog.png ``` ## Related Projects - **mlx-forge (conversion):** https://github.com/dgrauet/mlx-forge - **mlx-arsenal (reusable MLX ops):** https://github.com/dgrauet/mlx-arsenal - **mlx-porting (Claude Code skill):** https://github.com/dgrauet/claude-skill-mlx-porting ## Files - `model_index.json` (547.00 B) - `pe_tokenizer_tokenizer_config.json` (20.63 KB) - `quantize_config.json` (107.00 B) - `scheduler_scheduler_config.json` (482.00 B) - `special_tokens_map.json` (414.00 B) - `split_model.json` (203.00 B) - `text_encoder.safetensors` (3.39 GB) - `text_encoder_config.json` (1.64 KB) - `tokenizer.json` (8.83 MB) - `tokenizer_tokenizer_config.json` (379.00 B) - `transformer.safetensors` (8.11 GB) - `transformer_config.json` (422.00 B) - `vae.safetensors` (160.33 MB) - `vae_config.json` (836.00 B)

Note11 juil.huggingface.co/dgrauet/ernie-image-turbo-mlx-q8

Source context: 0 downloads · 1 likes · Library mlx · Repo dgrauet/ernie-image-turbo-mlx-q8