BI

bilingual-gpt-neox-4b

BilingualGGUF by mmngaUpdated 2023-09-08
Download on Hugging Face
Parameters3.8B
Context2K
Layers36
Architecturegptneox
Smallest quant2.2 GB
Quick answer

bilingual-gpt-neox-4b needs about 6.5 GB of memory at Q5_0 (a 2.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 2.2 GB (Q4_0) to 4.0 GB (Q8_0).

bilingual-gpt-neox-4b is a 3.8B-parameter Bilingual model in GGUF format, quantized by mmnga. Its trained context length is 2K tokens. The repository has 5 quant files, from 2.2 GB (Q4_0) to 4.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_02.2 GB 3.5 GB
Fits Get file →
Q4_12.4 GB 3.7 GB
Fits Get file →
Q5_02.6 GB 4.0 GB
Fits Get file →
Q5_12.9 GB 4.2 GB
Fits Get file →
Q8_04.0 GB 5.4 GB
Fits Get file →

What GPU do you need for bilingual-gpt-neox-4b?

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_0 (2.2 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q8_0 (4.0 GB file, about 7.9 GB in use).

Which bilingual-gpt-neox-4b quant should you choose?

Q5_0 (2.6 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q4_0 at 2.2 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

Architecturegptneox
Parameters3.8B
Layers36
Trained context2,048 tokens
KV cache (fp16)396 KB per token

Source

Quantized bymmnga
FamilyBilingual
Licensemit
Downloads (HF)91
Last updated2023-09-08

Frequently asked questions about bilingual-gpt-neox-4b

How much VRAM does bilingual-gpt-neox-4b need?

About 6.5 GB at Q5_0 with an 8K context window. That is the 2.6 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 bilingual-gpt-neox-4b on an 8 GB GPU?

Yes, with Q8_0: the 4.0 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bilingual-gpt-neox-4b GGUF?

It depends on the quant: Q4_0 is 2.2 GB, Q4_1 is 2.4 GB, Q5_0 is 2.6 GB, Q5_1 is 2.9 GB, Q8_0 is 4.0 GB.

What context length does bilingual-gpt-neox-4b support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 3.3 GB at 8K and 0.8 GB at 2K.

Where can I download bilingual-gpt-neox-4b GGUF?

The files are on Hugging Face in the mmnga/rinna-bilingual-gpt-neox-4b-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 bilingual-gpt-neox-4b use?

Hugging Face lists the license as mit. 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 mmnga

All by mmnga →

More Bilingual models

All Bilingual →

Other small models

All small models →