ERNIE Image Abliterated needs about 2.9 GB of memory at Q4_K_M (a 2.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 6 quants, from 2.1 GB (Q4_K_M) to 3.7 GB (Q8_0).
ERNIE Image Abliterated – a compact text‑to‑image model
ERNIE Image Abliterated is a 3.43 billion‑parameter model based on the Mistral3 architecture. It is a quantized version of Baidu’s ERNIE‑Image, designed for text‑to‑image generation with strong instruction following and structured layout capabilities.
Good at
- Text‑heavy image generation
- Structured poster and comic creation
- Multi‑panel layout synthesis
Limits
- No vision support in this GGUF version
- Requires 8 k context for estimates
- License is other, not open‑source
Best for
- Poster design
- Comic storyboard creation
- UI‑style image generation
Who it’s for. Developers and content creators who need a lightweight, instruction‑driven text‑to‑image model for structured visual tasks. The model is suitable for local deployment on consumer hardware.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q4_K_M | 2.1 GB | 2.9 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 3.7 GB | Fits | Get file → | |
| Q6_K | 2.8 GB | 3.7 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 3.7 GB | 4.6 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (2.15 GB file, 2.9 GB memory at 8 k context) is recommended. If more VRAM is available, Q6_K (2.82 GB file, 3.7 GB memory) offers higher quality. Q8_0 (3.65 GB file, 4.6 GB memory) requires larger memory budgets.
What GPU do you need for ERNIE Image Abliterated?
These figures add the file size, an fp16 KV cache at an 8K context window and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q6_K (2.8 GB file, about 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.7 GB file, about 4.6 GB in use).
Which ERNIE Image Abliterated quant should you choose?
Q4_K_M is the usual starting point for ERNIE Image Abliterated: it balances file size and quality well. Here it is a 2.1 GB file.
The Q8_0 file is 3.7 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ERNIE Image Abliterated
How much VRAM does ERNIE Image Abliterated need?
About 2.9 GB at Q4_K_M with an 8K context window. That is the 2.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run ERNIE Image Abliterated on an 8 GB GPU?
Yes, with Q8_0: the 3.7 GB file needs about 4.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ERNIE Image Abliterated GGUF?
It depends on the quant: Q4_K_M is 2.1 GB, Q4_K_M is 2.1 GB, Q6_K is 2.8 GB, Q6_K is 2.8 GB, Q8_0 is 3.7 GB, Q8_0 is 3.7 GB.
What context length does ERNIE Image Abliterated support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download ERNIE Image Abliterated GGUF?
The files are on Hugging Face in the ponpoke/ERNIE-Image-Abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does ERNIE Image Abliterated use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run this model on 8 GB VRAM?
Yes, the Q4_K_M quantization uses 2.9 GB memory at 8 k context, fitting within an 8 GB VRAM setup.
Does this model support vision inputs?
No, the GGUF version does not include vision capabilities.
What context length does it support?
It supports a trained context of 262144 tokens, but estimates are given for 8 k context.