SA

Sakura 13B LNovel v0.9b GGUF IMX wikitest

SakuraGGUF by shing3232Updated 2024-01-15
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architectureqwen
Smallest quant5.2 GB
Quick answer

Sakura 13B LNovel v0.9b GGUF IMX wikitest needs about 12.4 GB of memory at its main file (a 5.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 5.2 GB to 6.0 GB.

Sakura 13B LNovel v0.9b GGUF IMX wikitest is a 14.2B-parameter Sakura model in GGUF format, quantized by shing3232. Its trained context length is 8K tokens. The repository has 2 quant files, from 5.2 GB to 6.0 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—5.2 GB 12.4 GB
Too big Get file →
—6.0 GB 13.2 GB
Too big Get file →

What GPU do you need for Sakura 13B LNovel v0.9b GGUF IMX wikitest?

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: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is the main file (6.0 GB file, about 13.2 GB in use).

Specifications

Architecture from the GGUF header

Architectureqwen
Parameters14.2B
Layers40
Trained context8,192 tokens
KV cache (fp16)800 KB per token

Source

Quantized byshing3232
FamilySakura
Downloads (HF)31
Last updated2024-01-15

Frequently asked questions about Sakura 13B LNovel v0.9b GGUF IMX wikitest

How much VRAM does Sakura 13B LNovel v0.9b GGUF IMX wikitest need?

About 12.4 GB at its main file with an 8K context window. That is the 5.2 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 13B LNovel v0.9b GGUF IMX wikitest on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 12.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sakura 13B LNovel v0.9b GGUF IMX wikitest GGUF?

It depends on the quant: file is 5.2 GB, file is 6.0 GB.

What context length does Sakura 13B LNovel v0.9b GGUF IMX wikitest support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 6.7 GB at 8K and 6.7 GB at 8K.

Where can I download Sakura 13B LNovel v0.9b GGUF IMX wikitest GGUF?

The files are on Hugging Face in the shing3232/Sakura-13B-LNovel-v0.9b-GGUF-IMX-wikitest repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from shing3232

All by shing3232 →

More Sakura models

All Sakura →

Other medium models

All medium models →