Sakura GalTransl 7B v3.7 needs about 7.2 GB of memory at its main file (a 6.3 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 8 quants, from 4.3 GB (IQ4_XS) to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
Sakura GalTransl 7B v3.7 is a 7.72B-parameter Sakura model in GGUF format, quantized by chenniandexin. Its trained context length is 128K tokens. The repository has 8 quant files, from 4.3 GB (IQ4_XS) to 6.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 4.3 GB | 5.2 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.3 GB | Fits | Get file → | |
| — | 6.3 GB | 7.2 GB | Tight | Get file → | |
| Q6_K | 6.3 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.3 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.3 GB | 7.3 GB | Tight | Get file → | |
| Q6_K | 6.3 GB | 7.3 GB | Tight | Get file → |
What GPU do you need for Sakura GalTransl 7B v3.7?
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: the best quant that fits is IQ4_XS (4.3 GB file, about 5.2 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.3 GB in use).
Which Sakura GalTransl 7B v3.7 quant should you choose?
If memory is tight, the smallest file is IQ4_XS at 4.3 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 Sakura GalTransl 7B v3.7
How much VRAM does Sakura GalTransl 7B v3.7 need?
About 7.2 GB at its main file with an 8K context window. That is the 6.3 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 Sakura GalTransl 7B v3.7 on an 8 GB GPU?
Yes, with Q6_K: the 6.3 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sakura GalTransl 7B v3.7 GGUF?
It depends on the quant: IQ4_XS is 4.3 GB, Q5_K_S is 5.3 GB, Q5_K_S is 5.3 GB, file is 6.3 GB, Q6_K is 6.3 GB, Q6_K is 6.3 GB and 2 more.
What context length does Sakura GalTransl 7B v3.7 support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download Sakura GalTransl 7B v3.7 GGUF?
The files are on Hugging Face in the chenniandexin/Sakura-GalTransl-7B-v3.7 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Sakura GalTransl 7B v3.7 use?
Hugging Face lists the license as cc-by-nc-sa-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.