SA

Sakura GalTransl 14B v3.8

SakuraGGUF by SakuraLLMUpdated 2025-09-11
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant8.1 GB
Quick answer

Sakura GalTransl 14B v3.8 needs about 11.1 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 8.1 GB (IQ4_XS) to 12.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Sakura GalTransl 14B v3.8 – 14B Qwen2.5 based translation model

Sakura GalTransl 14B v3.8 is a 14‑billion parameter Qwen2 architecture model. It builds on the GalTransl‑v3 framework with improved style and fewer pronoun errors. The model supports 131072 context tokens and is released under CC‑BY‑NC‑SA‑4.0.

Good at

  • High‑quality translation
  • Long‑context handling
  • Stable control symbols

Limits

  • No vision support
  • Requires 8‑k context for estimates
  • License restricts commercial use

Best for

  • Translating long documents
  • Generating consistent narratives
  • Fine‑tuning on translation tasks

Who it’s for. Developers and researchers needing a large‑scale translation model for local deployment. The model is suitable for non‑commercial projects that require high context length and stable output.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ4_XS8.1 GB 10.2 GB
Too big Get file →
IQ4_XS8.2 GB 10.3 GB
Too big Get file →
IQ4_XS8.2 GB 10.3 GB
Too big Get file →
Q4_K_M9.0 GB 11.1 GB
Too big Get file →
Q5_K_S10.3 GB 12.4 GB
Too big Get file →
Q5_K_S10.3 GB 12.4 GB
Too big Get file →
Q5_K_S10.3 GB 12.4 GB
Too big Get file →
—12.1 GB 14.2 GB
Too big Get file →

For 8‑GB VRAM, use IQ4_XS (≈10.2 GB memory at 8k context). For 12‑GB VRAM, Q4_K_M (≈11.1 GB) or Q5_K_S (≈12.4 GB) are suitable. Larger memory budgets allow the unknown quant (~14.2 GB).

What GPU do you need for Sakura GalTransl 14B v3.8?

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: the best quant that fits is Q4_K_M (9.0 GB file, about 11.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (12.1 GB file, about 14.2 GB in use).

Which Sakura GalTransl 14B v3.8 quant should you choose?

Q4_K_M is the usual starting point for Sakura GalTransl 14B v3.8: it balances file size and quality well. Here it is a 9.0 GB file.

If memory is tight, the smallest file is IQ4_XS at 8.1 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

Architectureqwen2
Parameters14.8B
Layers48
Trained context131,072 tokens
KV cache (fp16)192 KB per token

Source

Quantized bySakuraLLM
FamilySakura
Downloads (HF)12,537
Last updated2025-09-11

Frequently asked questions about Sakura GalTransl 14B v3.8

How much VRAM does Sakura GalTransl 14B v3.8 need?

About 11.1 GB at Q4_K_M with an 8K context window. That is the 9.0 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 14B v3.8 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sakura GalTransl 14B v3.8 GGUF?

It depends on the quant: IQ4_XS is 8.1 GB, IQ4_XS is 8.2 GB, IQ4_XS is 8.2 GB, Q4_K_M is 9.0 GB, Q5_K_S is 10.3 GB, Q5_K_S is 10.3 GB and 2 more.

What context length does Sakura GalTransl 14B v3.8 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download Sakura GalTransl 14B v3.8 GGUF?

The files are on Hugging Face in the SakuraLLM/Sakura-GalTransl-14B-v3.8 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 14B v3.8 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.

Can I run Sakura GalTransl 14B v3.8 on 8 GB VRAM?

Yes, the IQ4_XS quant uses about 10.2 GB memory at 8k context, which fits 8 GB VRAM with some headroom.

What context length does the model support?

The model was trained with 131072 tokens and can handle up to that context length in inference.

Is the model suitable for commercial use?

No, the CC‑BY‑NC‑SA‑4.0 license prohibits commercial deployment.

Similar models

Browse all →

More from SakuraLLM

All by SakuraLLM →

More Sakura models

All Sakura →

Other medium models

All medium models →