SA

SakuraLLMSakura 13B LNovel v08

SakurallmsakuraGGUF by longodUpdated 2023-11-20
Download on Hugging Face
Parameters13.9B
Context4K
Layers40
Architecturebaichuan
Smallest quant6.5 GB
Quick answer

SakuraLLMSakura 13B LNovel v08 needs about 16.2 GB of memory at Q4_K_M (a 9.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 6.5 GB (Q2_K) to 27.8 GB (F16).

SakuraLLMSakura 13B LNovel v08 is a 13.9B-parameter Sakurallmsakura model in GGUF format, quantized by longod. Its trained context length is 4K tokens. The repository has 7 quant files, from 6.5 GB (Q2_K) to 27.8 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K6.5 GB 10.4 GB
Too big Get file →
Q3_K_M7.2 GB 11.1 GB
Too big Get file →
Q4_K_M9.0 GB 12.9 GB
Too big Get file →
Q5_K_M10.3 GB 14.2 GB
Too big Get file →
Q6_K12.1 GB 15.9 GB
Too big Get file →
Q8_014.8 GB 18.6 GB
Too big Get file →
F1627.8 GB 31.7 GB
Too big Get file →

What GPU do you need for SakuraLLMSakura 13B LNovel v08?

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 Q3_K_M (7.2 GB file, about 14.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 22.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (14.8 GB file, about 22.0 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (27.8 GB file, about 35.0 GB in use).

Which SakuraLLMSakura 13B LNovel v08 quant should you choose?

Q4_K_M is the usual starting point for SakuraLLMSakura 13B LNovel v08: it balances file size and quality well. Here it is a 9.0 GB file.

The Q8_0 file is 14.8 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 6.5 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebaichuan
Parameters13.9B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bylongod
Licenseunknown
Downloads (HF)76
Last updated2023-11-20

Frequently asked questions about SakuraLLMSakura 13B LNovel v08

How much VRAM does SakuraLLMSakura 13B LNovel v08 need?

About 16.2 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 SakuraLLMSakura 13B LNovel v08 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SakuraLLMSakura 13B LNovel v08 GGUF?

It depends on the quant: Q2_K is 6.5 GB, Q3_K_M is 7.2 GB, Q4_K_M is 9.0 GB, Q5_K_M is 10.3 GB, Q6_K is 12.1 GB, Q8_0 is 14.8 GB and 1 more.

What context length does SakuraLLMSakura 13B LNovel v08 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download SakuraLLMSakura 13B LNovel v08 GGUF?

The files are on Hugging Face in the longod/SakuraLLMSakura-13B-LNovel-v08-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 SakuraLLMSakura 13B LNovel v08 use?

Hugging Face lists the license as unknown. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

Other medium models

All medium models →