Skip to content
ModelVerifiedExternal
Browse files

Ernie Image Sft Mlx Q4

Int4 quantization (groupsize 64, attention and FFN Linear weights only, leaving the small projections and the VAE in bf16) of dgrauet/ernie-image-sft-mlx, the MLX conversion of baidu/ERNIE-Image.

Sourcehuggingface.co/dgrauet/ernie-image-sft-mlx-q4/tree/73a0f2ddf26266758033ee7f6d3606448f67945d
KindText modelBase modelbaidu/ERNIE-ImageVersionPublisher@dgrauetCgrade

Model source

Kind
Text model
File size
160 MB–4.45 GB
Base model
baidu/ERNIE-Image
Version
vRevision 73a0f2d
Updated
Oct 21, 2026
Publisher
@dgrauet
Downloads
0
Source
Hugging Face

Source description

dgrauet/ernie-image-sft-mlx-q4

Int4 quantization (group_size 64, attention and FFN Linear weights only, leaving the small projections and the VAE in bf16) of dgrauet/ernie-image-sft-mlx, the MLX conversion of baidu/ERNIE-Image.

Quantized with mlx-forge (mlx-forge convert ernie-image --variant sft --quantize --bits 4).

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-sft-mlx-q4 \
    -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 (1.07 KB)
  • text_encoder.safetensors (1.80 GB)
  • text_encoder_config.json (1.64 KB)
  • tokenizer.json (8.83 MB)
  • tokenizer_tokenizer_config.json (379.00 B)
  • transformer.safetensors (4.45 GB)
  • transformer_config.json (383.00 B)
  • vae.safetensors (160.33 MB)
  • vae_config.json (831.00 B)

Sources

1 source
Hugging FacePrimaryVersion 73a0f2ddf26266758033ee7f6d3606448f67945d
huggingface.co/dgrauet/ernie-image-sft-mlx-q4/tree/73a0f2ddf26266758033ee7f6d3606448f67945d

Verified Sep 27

Download files

Model artifacts

3 artifacts

text_encoder.safetensors

safetensors · 1.80 GB · SHA-256 7898b1da88c7…ebef · Hugging Face

Download file

transformer.safetensors

safetensors · 4.45 GB · SHA-256 b1e0ff4f7747…7a01 · Hugging Face

Download file

vae.safetensors

safetensors · 160 MB · SHA-256 1dde9f84839d…9230 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeSep 27huggingface.co/dgrauet/ernie-image-sft-mlx-q4

--- library_name: mlx license: apache-2.0 base_model: baidu/ERNIE-Image tags: - mlx - mlx-forge - apple-silicon - safetensors - quantized - int4 --- # dgrauet/ernie-image-sft-mlx-q4 Int4 quantization (group_size 64, attention and FFN Linear weights only, leaving the small projections and the VAE in bf16) of [dgrauet/ernie-image-sft-mlx](https://huggingface.co/dgrauet/ernie-image-sft-mlx), the MLX conversion of [baidu/ERNIE-Image](https://huggingface.co/baidu/ERNIE-Image). Quantized with [mlx-forge](https://github.com/dgrauet/mlx-forge) (`mlx-forge convert ernie-image --variant sft --quantize --bits 4`). ## 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-sft-mlx-q4 \ -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-sft-mlx - **q8 variant:** https://huggingface.co/dgrauet/ernie-image-sft-mlx-q8 ## 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` (1.07 KB) - `text_encoder.safetensors` (1.80 GB) - `text_encoder_config.json` (1.64 KB) - `tokenizer.json` (8.83 MB) - `tokenizer_tokenizer_config.json` (379.00 B) - `transformer.safetensors` (4.45 GB) - `transformer_config.json` (383.00 B) - `vae.safetensors` (160.33 MB) - `vae_config.json` (831.00 B)

ReadmeJul 11huggingface.co/dgrauet/ernie-image-sft-mlx-q4

--- library_name: mlx license: apache-2.0 base_model: baidu/ERNIE-Image tags: - mlx - mlx-forge - apple-silicon - safetensors --- # dgrauet/ernie-image-sft-mlx-q4 MLX format conversion of [baidu/ERNIE-Image](https://huggingface.co/baidu/ERNIE-Image). Converted with [mlx-forge](https://github.com/dgrauet/mlx-forge). - **Quantization:** int4 ## 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-sft-mlx-q4 \ -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` (195.00 B) - `text_encoder.safetensors` (1.80 GB) - `text_encoder_config.json` (1.64 KB) - `tokenizer.json` (8.83 MB) - `tokenizer_tokenizer_config.json` (379.00 B) - `transformer.safetensors` (4.45 GB) - `transformer_config.json` (383.00 B) - `vae.safetensors` (160.33 MB) - `vae_config.json` (831.00 B)

NoteJul 11huggingface.co/dgrauet/ernie-image-sft-mlx-q4

Source context: 0 downloads · 0 likes · Library mlx · Repo dgrauet/ernie-image-sft-mlx-q4