Wicked Tutu 31B Final needs about 51.4 GB of memory at Q4_K_M (a 18.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 18.7 GB (Q4_K_M) to 25.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 128.8 GB.
31‑billion‑parameter Gemma4 model focused on roleplay
Wicked Tutu 31B Final is a 31‑billion‑parameter Gemma4 model released under the Apache‑2.0 license. It supports a 262,144‑token context window and is optimized for role‑playing scenarios. The model is available in two quantized GGUF formats.
Good at
- Large context handling
- Role‑play dialogue
- High‑capacity language modeling
Limits
- Requires 51–58 GB VRAM at 8 k context
- No vision or multimodal support
- Apache‑2.0 license limits commercial use without attribution
Best for
- Interactive storytelling
- Chatbot development
- Creative writing assistance
Who it’s for. Developers building role‑play or narrative applications who need a large context window and are comfortable managing high VRAM requirements. The model is suitable for users with access to high‑end GPUs and who comply with the Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 18.7 GB | 51.4 GB | Too big | Get file → | |
| Q6_K | 25.2 GB | 57.9 GB | Too big | Get file → |
For 8 GB VRAM, the Q4_K_M quant (~18.69 GB) is the only option, but it still exceeds typical GPU limits. For 12 GB VRAM, Q4_K_M remains the best trade‑off. If you have 16 GB or more, Q6_K (~25.2 GB) offers higher quality but higher memory usage.
What GPU do you need for Wicked Tutu 31B Final?
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: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which Wicked Tutu 31B Final quant should you choose?
Q4_K_M is the usual starting point for Wicked Tutu 31B Final: it balances file size and quality well. Here it is a 18.7 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wicked Tutu 31B Final
How much VRAM does Wicked Tutu 31B Final need?
About 51.4 GB at Q4_K_M with an 8K context window. That is the 18.7 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 Wicked Tutu 31B Final on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 51.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Wicked Tutu 31B Final GGUF?
It depends on the quant: Q4_K_M is 18.7 GB, Q6_K is 25.2 GB.
What context length does Wicked Tutu 31B Final support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 32.2 GB at 8K and 128.8 GB at 32K.
Where can I download Wicked Tutu 31B Final GGUF?
The files are on Hugging Face in the ReadyArt/Wicked-Tutu-31B-Final-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 31B Final 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 31B Final on 8 GB VRAM?
No, the smallest quant requires over 50 GB VRAM at 8 k context, which exceeds 8 GB.
What license does this model use?
Apache‑2.0, which allows modification and redistribution with attribution.
Does the model support vision or multimodal inputs?
No, it is a text‑only model with no vision capabilities.