BI

ds 4bit

BitGGUF by datastreamsUpdated 2023-10-06
Download on Hugging Face
Parameters12.9B
Context2K
Layers40
Architecturegptneox
Smallest quant7.3 GB
Quick answer

ds 4bit needs about 14.5 GB of memory at Q4_0 (a 7.3 GB file) with an 8K context window, so it fits on a 16 GB GPU.

ds 4bit is a 12.9B-parameter Bit model in GGUF format, quantized by datastreams. Its trained context length is 2K tokens. The repository has 1 quant file, from 7.3 GB (Q4_0) to 7.3 GB (Q4_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.3 GB 9.5 GB
Too big Get file →

What GPU do you need for ds 4bit?

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_0 (7.3 GB file, about 14.5 GB in use).

Which ds 4bit quant should you choose?

Q4_0 (7.3 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

Architecturegptneox
Parameters12.9B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized bydatastreams
FamilyBit
Downloads (HF)4
Last updated2023-10-06

Frequently asked questions about ds 4bit

How much VRAM does ds 4bit need?

About 14.5 GB at Q4_0 with an 8K context window. That is the 7.3 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 ds 4bit on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ds 4bit GGUF?

It depends on the quant: Q4_0 is 7.3 GB.

What context length does ds 4bit 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 ds 4bit GGUF?

The files are on Hugging Face in the datastreams/ds-4bit repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ds 4bit use?

Hugging Face lists the license as cc-by-nc-2.0. 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 Bit models

All Bit →

Other medium models

All medium models →