MangaShift needs about 3.4 GB of memory at Q4_K_M (a 2.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.9 GB to 2.6 GB (Q4_K_M).
MangaShift is a 3.88B-parameter Mangashift model in GGUF format, quantized by MattyMroz. The repository has 2 quant files, from 0.9 GB to 2.6 GB (Q4_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.9 GB | 1.5 GB | Fits | Get file → | |
| Q4_K_M | 2.6 GB | 3.4 GB | Fits | Get file → |
What GPU do you need for MangaShift?
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 Q4_K_M (2.6 GB file, about 3.4 GB in use).
Which MangaShift quant should you choose?
Q4_K_M is the usual starting point for MangaShift: it balances file size and quality well. Here it is a 2.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.9 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 MangaShift
How much VRAM does MangaShift need?
About 3.4 GB at Q4_K_M with an 8K context window. That is the 2.6 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 MangaShift on an 8 GB GPU?
Yes, with Q4_K_M: the 2.6 GB file needs about 3.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of MangaShift GGUF?
It depends on the quant: file is 0.9 GB, Q4_K_M is 2.6 GB.
Where can I download MangaShift GGUF?
The files are on Hugging Face in the MattyMroz/MangaShift repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does MangaShift 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.