LLaDA Image needs about 13.6 GB of memory at Q5_K (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 6 quants, from 7.0 GB (Q8_0) to 17.7 GB (Q8_0).
LLaDA-Image: Unified 6.54B image generation and editing
LLaDA-Image is a 6.54B‑parameter open‑source model for high‑quality text‑to‑image generation and instruction‑guided editing. It supports realistic image generation, natural lighting, and coherent scenes. The model is released under apache‑2.0.
Good at
- High‑quality image generation
- Instruction‑guided editing
- Chinese–English text rendering
Limits
- No vision support beyond image generation
- Requires 50 steps for base model
- Large VRAM needed for higher quantizations
Best for
- Creative poster generation
- Text‑to‑image projects
- Reference‑preserving editing
Who it’s for. Developers and researchers needing a unified image generation and editing solution. The model is suitable for projects that require both high‑quality generation and precise editing without separate backbones.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 7.0 GB | 8.3 GB | Too big | Get file → | |
| Q4_K | 9.7 GB | 11.4 GB | Too big | Get file → | |
| Q5_K | 11.7 GB | 13.6 GB | Too big | Get file → | |
| F16 | 13.1 GB | 15.2 GB | Too big | Get file → | |
| Q6_K | 13.8 GB | 16.0 GB | Too big | Get file → | |
| Q8_0 | 17.7 GB | 20.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q8_0 (6.95 GB, 8.3 GB memory at 8k context). For 12 GB VRAM, Q4_K (9.69 GB, 11.4 GB memory) is suitable. For 16 GB VRAM, Q5_K (11.69 GB, 13.6 GB memory) offers a balance between size and performance.
What GPU do you need for LLaDA Image?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q4_K (9.7 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (13.8 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (17.7 GB file, about 20.3 GB in use).
Which LLaDA Image quant should you choose?
Q5_K (11.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is Q8_0 at 7.0 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LLaDA Image
How much VRAM does LLaDA Image need?
About 13.6 GB at Q5_K with an 8K context window. That is the 11.7 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 LLaDA Image on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of LLaDA Image GGUF?
It depends on the quant: Q8_0 is 7.0 GB, Q4_K is 9.7 GB, Q5_K is 11.7 GB, F16 is 13.1 GB, Q6_K is 13.8 GB, Q8_0 is 17.7 GB.
Where can I download LLaDA Image GGUF?
The files are on Hugging Face in the fszontagh/LLaDA-Image-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 LLaDA Image use?
Hugging Face lists the license as apache-2.0. 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 LLaDA-Image on 8 GB VRAM?
Yes, the Q8_0 quantization is 6.95 GB and requires approximately 8.3 GB memory at 8k context.
Does LLaDA-Image support Chinese text rendering?
Yes, the model supports Chinese–English text rendering as part of its multilingual capabilities.