NovelAI Krake v2 needs about 50.5 GB of memory at F16 (a 41.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds.
NovelAI Krake v2 is a 20.6B-parameter Novelai model in GGUF format, quantized by onicubag. Its trained context length is 2K tokens. The repository has 1 quant file, from 41.1 GB (F16) to 41.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 41.1 GB | 43.8 GB | Too big | Get file → |
What GPU do you need for NovelAI Krake v2?
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 NovelAI Krake v2 quant should you choose?
F16 (41.1 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about NovelAI Krake v2
How much VRAM does NovelAI Krake v2 need?
About 50.5 GB at F16 with an 8K context window. That is the 41.1 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 NovelAI Krake v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 50.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of NovelAI Krake v2 GGUF?
It depends on the quant: F16 is 41.1 GB.
What context length does NovelAI Krake v2 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 8.9 GB at 8K and 2.2 GB at 2K.
Where can I download NovelAI Krake v2 GGUF?
The files are on Hugging Face in the onicubag/NovelAI-Krake-v2-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 NovelAI Krake v2 use?
Hugging Face lists the license as gpl-3.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.