QW

sakura-14b-qwen2.5-v1.0-iq4xs

QwenGGUF by SakuraLLMUpdated 2024-10-15
Download on Hugging Face
Parameters14.8B
Context128K
Layers48
Architectureqwen2
Smallest quant8.2 GB
Quick answer

sakura-14b-qwen2.5-v1.0-iq4xs needs about 11.1 GB of memory at its main file (a 9.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 8.2 GB to 12.1 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

Sakura-14B Qwen2.5 model optimized for translation and control

Sakura-14B Qwen2.5 is a 14‑billion parameter language model. It offers improved translation accuracy and better handling of control symbols. The model supports a 131072 token context window.

Good at

  • High‑quality translation
  • Consistent handling of pronouns
  • Preservation of control symbols

Limits

  • No vision support
  • CC‑BY‑NC‑SA‑4.0 license
  • Large VRAM requirement

Best for

  • Translation pipelines
  • Multilingual chatbots
  • Custom control‑symbol applications

Who it’s for. Developers building translation services or chatbots that require precise pronoun handling and control symbol preservation. Suitable for teams with GPU resources and a need for non‑commercial use.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.2 GB 10.3 GB
Too big Get file →
—9.0 GB 11.1 GB
Too big Get file →
—12.1 GB 14.2 GB
Too big Get file →

The 8.19 GB file needs about 10.3 GB VRAM at 8 k context. The 8.99 GB file requires ~11.1 GB VRAM. The 12.12 GB file needs ~14.2 GB VRAM. Choose the smallest file that fits your GPU memory budget.

What GPU do you need for sakura-14b-qwen2.5-v1.0-iq4xs?

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 the main file (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-14b-qwen2.5-v1.0-iq4xs quant should you choose?

If memory is tight, the smallest file is the first one in the table at 8.2 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

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

Source

Quantized bySakuraLLM
FamilyQwen
Downloads (HF)14,250
Last updated2024-10-15

Frequently asked questions about sakura-14b-qwen2.5-v1.0-iq4xs

How much VRAM does sakura-14b-qwen2.5-v1.0-iq4xs need?

About 11.1 GB at its main file 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-14b-qwen2.5-v1.0-iq4xs on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of sakura-14b-qwen2.5-v1.0-iq4xs GGUF?

It depends on the quant: file is 8.2 GB, file is 9.0 GB, file is 12.1 GB.

What context length does sakura-14b-qwen2.5-v1.0-iq4xs 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-14b-qwen2.5-v1.0-iq4xs GGUF?

The files are on Hugging Face in the SakuraLLM/Sakura-14B-Qwen2.5-v1.0-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 sakura-14b-qwen2.5-v1.0-iq4xs 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 this model on 8 GB VRAM?

The smallest file requires ~10.3 GB VRAM at 8 k context, so 8 GB is insufficient.

Does this model support vision tasks?

No, the model has no vision capabilities.

What license does it use?

It is released under CC‑BY‑NC‑SA‑4.0, allowing non‑commercial use with attribution.

Similar models

Browse all →

More from SakuraLLM

All by SakuraLLM →

More Qwen models

All Qwen →

Other medium models

All medium models →