WanT2IHighRealism2.2 needs about 17.8 GB of memory at Q8_0 (a 15.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 15.4 GB (Q8_0) to 15.4 GB (Q8_0).
WanT2IHighRealism2.2 – 14.3B parameter image generation model
WanT2IHighRealism2.2 is a 14.3 billion parameter model designed for high‑realism image generation. It is available in a Q8_0 quantized GGUF format. The model was trained by Kolso14 and released under an unknown license.
Good at
- High‑realism image generation
- Large parameter count for detailed visuals
- Q8_0 quantization for full precision
Limits
- No context length specified
- Requires ~17.8 GB VRAM at 8k context
- License unknown
Best for
- Creating detailed photorealistic images
- Generating high‑resolution artwork
- Producing realistic visual content
Who it’s for. Developers and artists who need a large‑parameter image generation model with full precision. Suitable for environments with ample VRAM and no strict licensing constraints.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 15.4 GB | 17.8 GB | Too big | Get file → | |
| Q8_0 | 15.4 GB | 17.8 GB | Too big | Get file → |
For systems with 20 GB VRAM, use the Q8_0 quantized file (15.4 GB). This provides full precision and requires approximately 17.8 GB VRAM at 8k context. No other quantizations are available.
What GPU do you need for WanT2IHighRealism2.2?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q8_0 (15.4 GB file, about 17.8 GB in use).
Which WanT2IHighRealism2.2 quant should you choose?
Q8_0 (15.4 GB) is the middle option in this repository. 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 WanT2IHighRealism2.2
How much VRAM does WanT2IHighRealism2.2 need?
About 17.8 GB at Q8_0 with an 8K context window. That is the 15.4 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 WanT2IHighRealism2.2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of WanT2IHighRealism2.2 GGUF?
It depends on the quant: Q8_0 is 15.4 GB, Q8_0 is 15.4 GB.
Where can I download WanT2IHighRealism2.2 GGUF?
The files are on Hugging Face in the Kolso14/WanT2IHighRealism2.2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does WanT2IHighRealism2.2 use?
Hugging Face lists the license as unknown. 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 WanT2IHighRealism2.2 on 8 GB VRAM?
No. The model requires about 17.8 GB VRAM at 8k context, so 8 GB is insufficient.
What quantization is available for this model?
Only Q8_0 is provided, with a file size of 15.4 GB.
Is there a license restriction?
The license is listed as unknown, so verify usage rights before deployment.