NE

neko

NekoGGUF by meditadorUpdated 2023-10-28
Download on Hugging Face
Parameters13B
Context2K
Layers40
Architecturellama
Smallest quant7.9 GB
Quick answer

neko needs about 15.1 GB of memory at Q4_K (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU.

neko is a 13B-parameter Neko model in GGUF format, quantized by meditador. Its trained context length is 2K tokens. The repository has 1 quant file, from 7.9 GB (Q4_K) to 7.9 GB (Q4_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K7.9 GB 10.0 GB
Too big Get file →

What GPU do you need for neko?

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 Q4_K (7.9 GB file, about 15.1 GB in use).

Which neko quant should you choose?

Q4_K (7.9 GB) is the middle option in this repository. 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

Architecturellama
Parameters13B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymeditador
FamilyNeko
Repositorymeditador/neko
Licenseunknown
Downloads (HF)3
Last updated2023-10-28

Frequently asked questions about neko

How much VRAM does neko need?

About 15.1 GB at Q4_K with an 8K context window. That is the 7.9 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 neko on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of neko GGUF?

It depends on the quant: Q4_K is 7.9 GB.

What context length does neko support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download neko GGUF?

The files are on Hugging Face in the meditador/neko repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does neko 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 →

More from meditador

All by meditador →

More Neko models

All Neko →

Other medium models

All medium models →