SA

Sakura 14B LNovel v0.9b

SakuraGGUF by SakuraLLMUpdated 2024-06-26
Download on Hugging Face
Parameters14.2B
Context8K
Layers40
Architectureqwen
Smallest quant5.7 GB
Quick answer

Sakura 14B LNovel v0.9b needs about 16.7 GB of memory at Q4_K_M (a 9.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 5 quants, from 5.7 GB (Q2_K) to 12.3 GB (Q6_K).

Sakura 14B LNovel v0.9b – 14.2B parameter LLM for novel writing

Sakura 14B LNovel v0.9b is a 14.2B parameter model built on the qwen architecture. It supports a 8192 token context window and is released under a CC‑BY‑NC‑SA‑4.0 license. The model is optimized for text generation tasks such as novel writing.

Good at

  • Long‑form creative writing
  • Dialogue generation
  • Story continuation

Limits

  • No vision support
  • License restricts commercial use
  • Requires 8k context for full performance

Best for

  • Writing short stories
  • Generating character dialogues
  • Drafting novel chapters

Who it’s for. Developers and writers who need a large‑parameter model for creative text generation. The model is suitable for non‑commercial projects that can comply with the CC‑BY‑NC‑SA‑4.0 license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.7 GB 13.0 GB
Too big Get file →
Q3_K_M7.7 GB 14.9 GB
Too big Get file →
Q4_K_M9.4 GB 16.7 GB
Too big Get file →
Q5_K_M10.9 GB 18.1 GB
Too big Get file →
Q6_K12.3 GB 19.5 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (5.74 GB file, ~13 GB memory). For 12 GB VRAM, Q3_K_M (7.69 GB file, ~14.9 GB memory) is suitable. If you have 16 GB VRAM, Q4_K_M (9.45 GB file, ~16.7 GB memory) offers a good balance of size and performance.

What GPU do you need for Sakura 14B LNovel v0.9b?

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 (7.7 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (12.3 GB file, about 19.5 GB in use).

Which Sakura 14B LNovel v0.9b quant should you choose?

Q4_K_M is the usual starting point for Sakura 14B LNovel v0.9b: it balances file size and quality well. Here it is a 9.4 GB file.

If memory is tight, the smallest file is Q2_K at 5.7 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

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

Source

Quantized bySakuraLLM
FamilySakura
Downloads (HF)1,642
Last updated2024-06-26

Frequently asked questions about Sakura 14B LNovel v0.9b

How much VRAM does Sakura 14B LNovel v0.9b need?

About 16.7 GB at Q4_K_M with an 8K context window. That is the 9.4 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 LNovel v0.9b on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sakura 14B LNovel v0.9b GGUF?

It depends on the quant: Q2_K is 5.7 GB, Q3_K_M is 7.7 GB, Q4_K_M is 9.4 GB, Q5_K_M is 10.9 GB, Q6_K is 12.3 GB.

What context length does Sakura 14B LNovel v0.9b 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 14B LNovel v0.9b GGUF?

The files are on Hugging Face in the SakuraLLM/Sakura-14B-LNovel-v0.9b-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 LNovel v0.9b 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 14B LNovel on 8 GB VRAM?

Yes, the Q2_K quantized model is 5.74 GB and requires about 13 GB of VRAM at 8k context, which is close to 8 GB but may need swapping.

Is this model suitable for commercial use?

No, the CC‑BY‑NC‑SA‑4.0 license prohibits commercial use without permission.

Does the model support image inputs?

No, Sakura 14B LNovel is a text‑only model with no vision capabilities.

Similar models

Browse all →

More from SakuraLLM

All by SakuraLLM →

More Sakura models

All Sakura →

Other medium models

All medium models →