QW

Sakura 13B Qwen2beta v0.10pre0

QwenGGUF by Tabing010102Updated 2024-03-07
Download on Hugging Face
Parameters14.2B
Context32K
Layers40
Architectureqwen2
Smallest quant9.0 GB
Quick answer

Sakura 13B Qwen2beta v0.10pre0 needs about 19.5 GB of memory at Q6_K (a 12.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 9.0 GB (Q4_1) to 15.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 26.8 GB.

Sakura 13B Qwen2beta v0.10pre0 is a 14.2B-parameter Qwen model in GGUF format, quantized by Tabing010102. Its trained context length is 32K tokens. The repository has 3 quant files, from 9.0 GB (Q4_1) to 15.1 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_19.0 GB 16.2 GB
Too big Get file →
Q6_K12.3 GB 19.5 GB
Too big Get file →
Q8_015.1 GB 22.3 GB
Too big Get file →

What GPU do you need for Sakura 13B Qwen2beta v0.10pre0?

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: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.1 GB file, about 22.3 GB in use).

Which Sakura 13B Qwen2beta v0.10pre0 quant should you choose?

Q6_K (12.3 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_1 at 9.0 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
Parameters14.2B
Layers40
Trained context32,768 tokens
KV cache (fp16)800 KB per token

Source

Quantized byTabing010102
FamilyQwen
Licensegpl-3.0
Downloads (HF)36
Last updated2024-03-07

Frequently asked questions about Sakura 13B Qwen2beta v0.10pre0

How much VRAM does Sakura 13B Qwen2beta v0.10pre0 need?

About 19.5 GB at Q6_K with an 8K context window. That is the 12.3 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 Qwen2beta v0.10pre0 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Sakura 13B Qwen2beta v0.10pre0 GGUF?

It depends on the quant: Q4_1 is 9.0 GB, Q6_K is 12.3 GB, Q8_0 is 15.1 GB.

What context length does Sakura 13B Qwen2beta v0.10pre0 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 6.7 GB at 8K and 26.8 GB at 32K.

Where can I download Sakura 13B Qwen2beta v0.10pre0 GGUF?

The files are on Hugging Face in the Tabing010102/Sakura-13B-Qwen2beta-v0.10pre0-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 13B Qwen2beta v0.10pre0 use?

Hugging Face lists the license as gpl-3.0. 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 →

More Qwen models

All Qwen →

Other medium models

All medium models →