K3 Stuff needs about 3.2 GB of memory at Q8_0 (a 2.4 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.3 GB (Q4_K) to 1480.8 GB (Q4_K_XL).
K3 Stuff is a 2780B-parameter Stuff model in GGUF format, quantized by TessaCoil. Its trained context length is 1024K tokens. The repository has 3 quant files, from 1.3 GB (Q4_K) to 1480.8 GB (Q4_K_XL).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 1.3 GB | 2.0 GB | Fits | Get file → | |
| Q8_0 | 2.4 GB | 3.2 GB | Fits | Get file → | |
| Q4_K_XL | 1480.8 GB (32 parts) | 1658.9 GB | Too big | Get file → |
What GPU do you need for K3 Stuff?
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: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (2.4 GB file, about 3.2 GB in use).
Which K3 Stuff quant should you choose?
Q8_0 (2.4 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.
If memory is tight, the smallest file is Q4_K at 1.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about K3 Stuff
How much VRAM does K3 Stuff need?
About 3.2 GB at Q8_0 with an 8K context window. That is the 2.4 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 K3 Stuff on an 8 GB GPU?
Yes, with Q8_0: the 2.4 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of K3 Stuff GGUF?
It depends on the quant: Q4_K is 1.3 GB, Q8_0 is 2.4 GB, Q4_K_XL is 1480.8 GB.
What context length does K3 Stuff support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download K3 Stuff GGUF?
The files are on Hugging Face in the TessaCoil/K3-Stuff repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does K3 Stuff use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.