Wicked Tutu 26B A4B needs about 27.1 GB of memory at Q4_K_M (a 18.6 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 4 quants, from 18.6 GB (Q4_K_M) to 27.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Wicked Tutu 26B A4B – 25.2B parameter gemma4 model
Wicked Tutu 26B A4B is a 25.2B parameter gemma4 model with a mixture of experts architecture. It supports roleplay tasks and is licensed under apache-2.0. The model was trained on 262144 context tokens.
Good at
- Roleplay
- Large context handling
- Mixture of experts
Limits
- No vision support
- Requires high VRAM for full precision
- Limited to 262144 token context
Best for
- Interactive storytelling
- Dialogue generation
- Character simulation
Who it’s for. Developers and researchers needing a large gemma4 model for roleplay and dialogue tasks. The model is suitable for applications that can handle the memory demands of a 26B parameter mixture of experts architecture.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 18.6 GB | 27.1 GB | Too big | Get file → | |
| Q5_K_M | 20.8 GB | 29.3 GB | Too big | Get file → | |
| Q6_K | 24.2 GB | 32.7 GB | Too big | Get file → | |
| Q8_0 | 27.9 GB | 36.5 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (18.58 GB file, ~27.1 GB memory at 8 k context). For 12 GB VRAM use Q5_K_M (20.79 GB file, ~29.3 GB memory). For 16 GB VRAM use Q6_K (24.16 GB file, ~32.7 GB memory).
What GPU do you need for Wicked Tutu 26B A4B?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) 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: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is Q5_K_M (20.8 GB file, about 29.3 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (27.9 GB file, about 36.5 GB in use).
Which Wicked Tutu 26B A4B quant should you choose?
Q4_K_M is the usual starting point for Wicked Tutu 26B A4B: it balances file size and quality well. Here it is a 18.6 GB file.
The Q8_0 file is 27.9 GB, about 1.5 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 Wicked Tutu 26B A4B
How much VRAM does Wicked Tutu 26B A4B need?
About 27.1 GB at Q4_K_M with an 8K context window. That is the 18.6 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 Wicked Tutu 26B A4B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 27.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Wicked Tutu 26B A4B GGUF?
It depends on the quant: Q4_K_M is 18.6 GB, Q5_K_M is 20.8 GB, Q6_K is 24.2 GB, Q8_0 is 27.9 GB.
What context length does Wicked Tutu 26B A4B support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Wicked Tutu 26B A4B GGUF?
The files are on Hugging Face in the ReadyArt/Wicked-Tutu-26B-A4B-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 Wicked Tutu 26B A4B 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 Wicked Tutu 26B A4B on 8 GB VRAM?
Use the Q4_K_M quantized file; it requires about 27.1 GB memory at 8 k context, so 8 GB VRAM is insufficient.
Does the model support image inputs?
No, the model has no vision support.
What license applies to this model?
The model is released under the apache-2.0 license.