---

license: apache-2.0

base_model:

- mistralai/Ministral-3-3B-Base-2512

- baidu/ERNIE-Image

library_name: gguf

tags:

- gguf

- stable-diffusion.cpp

- text-encoder

- ernie-image

- ministral

---

Ministral-3-3B-Base text encoder for ERNIE-Image — stable-diffusion.cpp GGUF

Unofficial GGUF conversion of the text encoder used by ERNIE-Image

and ERNIE-Image-Turbo, prepared for

stable-diffusion.cpp (--llm).

Not affiliated with Baidu or Mistral AI.

Files

| File | Type | Size | SHA-256 |

|---|---|---|---|

| ministral-3-3b-base-text-Q4_K.gguf | q4_K | 1.93 GB | 2203200a4943cee09b531fdb9cb4e5e9d23c55aad13c16e7213c74f03243d677 |

| ministral-3-3b-base-text-Q6_K.gguf | q6_K | 2.81 GB | 92e2f0af8dfbb536311d230e878e768a061536d8ba15f71998e24a83ae315744 |

| ministral-3-3b-base-text-Q8_0.gguf | q8_0 | 3.64 GB | 7f02e385cf6ab93b19b186641c66c1ea3a0fd7f84d0caea1ebee3c739796fbc9 |

What was changed

The ERNIE-Image text_encoder/ is a Mistral3Model whose language model is byte-identical to

mistralai/Ministral-3-3B-Base-2512 (spot-checked tensors match). ERNIE-Image uses the second-to-last

hidden state of that language model. For stable-diffusion.cpp:

1. only the language-model tensors (language_model.model.*) were kept; the vision tower and projector were dropped,
2. tensors were renamed to the text-only model.* layout that stable-diffusion.cpp expects,
3. weights were quantized with sd-cli -M convert --type {q4_K,q6_K,q8_0} (stable-diffusion.cpp master-899-28b454b).

No weights were fine-tuned or otherwise modified.

Usage (stable-diffusion.cpp)

# diffusion model: unsloth/ERNIE-Image-Turbo-GGUF, VAE: baidu/ERNIE-Image (vae/)
sd-cli \
  --diffusion-model ernie-image-turbo-UD-Q4_K_M.gguf \
  --vae diffusion_pytorch_model.safetensors \
  --llm ministral-3-3b-base-text-Q6_K.gguf \
  --diffusion-fa --steps 8 --cfg-scale 1.0 -W 512 -H 512 \
  -p "a friendly robot mascot" -o out.png

These files use stable-diffusion.cpp tensor naming and may not load in other runtimes (ComfyUI, llama.cpp).

License

Apache License 2.0, same as the original weights

(baidu/ERNIE-Image,

mistralai/Ministral-3-3B-Base-2512).

See LICENSE. Modifications: tensor subset/renaming and quantization as described above.