Wicked Stuff 26B A4B v3.0 Final needs about 26.5 GB of memory at Q4_K_M (a 18.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 50.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 32.2 GB.
Wicked Stuff 26B A4B v3.0 Final – a 26B gemma4 model with vision, reasoning, roleplay and tools.
Wicked Stuff 26B A4B v3.0 Final is a 26B parameter gemma4 model with 4B active parameters in a mixture of experts. It supports text, image and audio inputs and was trained on 262144 context tokens. The model is available in multiple GGUF quantizations.
Good at
- Reasoning
- Roleplay
- Vision and audio support
Limits
- No speculative decoding
- License not specified
- Large VRAM requirement for high‑quality quant
Best for
- Chatbots needing multimodal input
- Creative writing with image prompts
- Tool‑enabled task automation
Who it’s for. Developers and researchers who need a large multimodal LLM that can be run locally with llama.cpp. The model is suitable for applications that require reasoning, roleplay, and vision or audio processing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 8.7 GB | Too big | Get file → | |
| IQ2_XS | 9.9 GB | 18.4 GB | Too big | Get file → | |
| IQ2_S | 10.3 GB | 18.9 GB | Too big | Get file → | |
| IQ2_M | 10.9 GB | 19.5 GB | Too big | Get file → | |
| Q2_K | 11.6 GB | 20.2 GB | Too big | Get file → | |
| Q3_K_S | 12.4 GB | 20.9 GB | Too big | Get file → | |
| IQ3_XXS | 12.6 GB | 21.2 GB | Too big | Get file → | |
| IQ3_XS | 12.8 GB | 21.4 GB | Too big | Get file → | |
| Q3_K_M | 13.8 GB | 22.3 GB | Too big | Get file → | |
| IQ4_XS | 14.3 GB | 22.8 GB | Too big | Get file → | |
| Q4_0 | 14.8 GB | 23.3 GB | Too big | Get file → | |
| Q3_K_L | 14.8 GB | 23.4 GB | Too big | Get file → | |
| IQ4_NL | 15.6 GB | 24.2 GB | Too big | Get file → | |
| Q4_K_S | 16.1 GB | 24.6 GB | Too big | Get file → | |
| Q4_1 | 16.1 GB | 24.7 GB | Too big | Get file → | |
| Q4_K_M | 18.0 GB | 26.5 GB | Too big | Get file → | |
| Q4_K_L | 18.2 GB | 26.8 GB | Too big | Get file → | |
| Q5_K_S | 18.4 GB | 27.0 GB | Too big | Get file → | |
| Q5_K_M | 20.0 GB | 28.6 GB | Too big | Get file → | |
| Q6_K_S | 23.1 GB | 31.7 GB | Too big | Get file → | |
| Q6_K | 23.8 GB | 32.3 GB | Too big | Get file → | |
| Q6_K_L | 24.5 GB | 33.1 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 35.4 GB | Too big | Get file → | |
| BF16 | 50.5 GB | 59.1 GB | Too big | Get file → |
For 8‑GB VRAM use IQ2_XS (9.9 GB) or IQ2_S (10.31 GB). For 16‑GB VRAM use Q4_K_M (17.97 GB) or Q5_K_M (20.01 GB). For 24‑GB VRAM use Q6_K (23.79 GB) or Q8_0 (26.86 GB). Memory estimates are approximate.
What GPU do you need for Wicked Stuff 26B A4B v3.0 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: the best quant that fits is the main file (0.1 GB file, about 8.7 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 8.7 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_L (14.8 GB file, about 23.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_S (23.1 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 35.4 GB in use).
Which Wicked Stuff 26B A4B v3.0 Final quant should you choose?
Q4_K_M is the usual starting point for Wicked Stuff 26B A4B v3.0 Final: it balances file size and quality well. Here it is a 18.0 GB file.
The Q8_0 file is 26.9 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.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Wicked Stuff 26B A4B v3.0 Final
How much VRAM does Wicked Stuff 26B A4B v3.0 Final need?
About 26.5 GB at Q4_K_M with an 8K context window. That is the 18.0 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 Stuff 26B A4B v3.0 Final on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Wicked Stuff 26B A4B v3.0 Final GGUF?
It depends on the quant: file is 0.1 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.3 GB, IQ2_M is 10.9 GB, Q2_K is 11.6 GB, Q3_K_S is 12.4 GB and 18 more.
What context length does Wicked Stuff 26B A4B v3.0 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 8.1 GB at 8K and 32.2 GB at 32K.
Where can I download Wicked Stuff 26B A4B v3.0 Final GGUF?
The files are on Hugging Face in the bartowski/ReadyArt_Wicked-Stuff-26B-A4B-v3.0-Final-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run this model on 8 GB VRAM?
Use the IQ2_XS or IQ2_S quantization, which are 9.9 GB and 10.31 GB respectively, and will fit on 8 GB VRAM with some swapping.
Does this model support vision?
Yes, it supports image and audio inputs as part of its multimodal capabilities.
Is there a license for this model?
No license information is provided in the supplied data.