NE

neither

NeitherGGUF by parsee-mizuhashiUpdated 2024-01-27
Download on Hugging Face
Parameters3.43B
Context2K
Layers26
Architecturellama
Smallest quant2.0 GB
Quick answer

neither needs about 5.4 GB of memory at Q4_1 (a 2.2 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 2.0 GB (Q4_0) to 3.6 GB (Q8_0).

neither is a 3.43B-parameter Neither model in GGUF format, quantized by parsee-mizuhashi. Its trained context length is 2K tokens. The repository has 3 quant files, from 2.0 GB (Q4_0) to 3.6 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.0 GB 3.2 GB
Fits Get file →
Q4_12.2 GB 3.4 GB
Fits Get file →
Q8_03.6 GB 4.8 GB
Fits Get file →

What GPU do you need for neither?

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: the best quant that fits is Q4_1 (2.2 GB file, about 5.4 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (3.6 GB file, about 6.9 GB in use).

Which neither quant should you choose?

Q4_1 (2.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

If memory is tight, the smallest file is Q4_0 at 2.0 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

Architecturellama
Parameters3.43B
Layers26
Trained context2,048 tokens
KV cache (fp16)325 KB per token

Source

Quantized byparsee-mizuhashi
FamilyNeither
Downloads (HF)19
Last updated2024-01-27

Frequently asked questions about neither

How much VRAM does neither need?

About 5.4 GB at Q4_1 with an 8K context window. That is the 2.2 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 neither on an 8 GB GPU?

Yes, with Q8_0: the 3.6 GB file needs about 6.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of neither GGUF?

It depends on the quant: Q4_0 is 2.0 GB, Q4_1 is 2.2 GB, Q8_0 is 3.6 GB.

What context length does neither support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.7 GB at 8K and 0.7 GB at 2K.

Where can I download neither GGUF?

The files are on Hugging Face in the parsee-mizuhashi/neither 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 →

Other tiny models

All tiny models →