Koto 22B PT needs about 12.8 GB of memory at Q3_K_S (a 9.8 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 10.2 GB.
Koto 22B PT is a 22.1B-parameter Koto model in GGUF format, quantized by StellarDragon. Its trained context length is 128K tokens. The repository has 1 quant file, from 9.8 GB (Q3_K_S) to 9.8 GB (Q3_K_S).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 9.8 GB | 12.8 GB | Too big | Get file → |
What GPU do you need for Koto 22B PT?
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: the best quant that fits is Q3_K_S (9.8 GB file, about 12.8 GB in use).
Which Koto 22B PT quant should you choose?
Q3_K_S (9.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Koto 22B PT
How much VRAM does Koto 22B PT need?
About 12.8 GB at Q3_K_S with an 8K context window. That is the 9.8 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 Koto 22B PT on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Koto 22B PT GGUF?
It depends on the quant: Q3_K_S is 9.8 GB.
What context length does Koto 22B PT support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.6 GB at 8K and 10.2 GB at 32K.
Where can I download Koto 22B PT GGUF?
The files are on Hugging Face in the StellarDragon/Koto-22B-PT-Q3_K_S-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 Koto 22B PT 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.