Wanabi_Novelist_12B needs about 9.3 GB of memory at Q4_K_M (a 7.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 13 quants, from 4.9 GB (IQ3_XXS) to 24.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Wanabi_Novelist_12B – Japanese novel writing assistant
Wanabi_Novelist_12B is a 12.2B‑parameter llama model fine‑tuned for novel generation. It is designed to work with Project Wannabe and koboldcpp. The model supports generation, continuation, and idea creation tasks with rating and dialogue control.
Good at
- Novel generation in Japanese
- Idea and plot development
- Continuation of existing text
Limits
- No general instruction response capability
- Requires Project Wannabe update
- Maximum training context 32K tokens
Best for
- Writing Japanese fiction
- Drafting plot outlines
- Extending existing manuscript
Who it’s for. Users of Project Wannabe seeking a dedicated Japanese novel writing model. The model is not intended for general-purpose instruction following.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ3_XXS | 4.9 GB | 6.8 GB | Fits | Get file → | |
| Q3_K_M | 6.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_M | 6.1 GB | 7.9 GB | Tight | Get file → | |
| IQ4_XS | 6.7 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_M | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_M | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → | |
| BF16 | 24.5 GB | 26.3 GB | Too big | Get file → |
For 8 GB VRAM, use IQ3_XXS (4.95 GB, 6.8 GB memory at 8K context). For 12 GB VRAM, use Q4_K_M (7.48 GB, 9.3 GB memory). For 16 GB VRAM, use Q5_K_M (8.73 GB, 10.6 GB memory).
What GPU do you need for Wanabi_Novelist_12B?
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: the best quant that fits is Q3_K_M (6.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (24.5 GB file, about 26.3 GB in use).
Which Wanabi_Novelist_12B quant should you choose?
Q4_K_M is the usual starting point for Wanabi_Novelist_12B: it balances file size and quality well. Here it is a 7.5 GB file.
The Q8_0 file is 13.0 GB, about 1.7 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 IQ3_XXS at 4.9 GB, with the quality trade-offs that come with fewer bits. 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 Wanabi_Novelist_12B
How much VRAM does Wanabi_Novelist_12B need?
About 9.3 GB at Q4_K_M with an 8K context window. That is the 7.5 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 Wanabi_Novelist_12B on an 8 GB GPU?
Yes, with Q3_K_M: the 6.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Wanabi_Novelist_12B GGUF?
It depends on the quant: IQ3_XXS is 4.9 GB, Q3_K_M is 6.1 GB, Q3_K_M is 6.1 GB, IQ4_XS is 6.7 GB, Q4_K_M is 7.5 GB, Q4_K_M is 7.5 GB and 7 more.
What context length does Wanabi_Novelist_12B support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Wanabi_Novelist_12B GGUF?
The files are on Hugging Face in the kawaimasa/Wanabi-Novelist-12B-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 Wanabi_Novelist_12B 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 Wanabi_Novelist_12B on 8 GB VRAM?
Yes, the IQ3_XXS quantized model is 4.95 GB and requires approximately 6.8 GB memory at 8K context.
Does the model support vision or multimodal input?
No, the model is purely text‑based and does not support vision.
What license applies to this model?
The model is released under the apache-2.0 license.