SA

SabbatH 2x7B

SabbathGGUF by ElizezenUpdated 2024-04-18
Download on Hugging Face
Parameters12.9B
Context4K
Layers32
Architecturellama
Smallest quant7.3 GB
Quick answer

SabbatH 2x7B needs about 8.9 GB of memory at Q4_0 (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.3 GB (Q4_0) to 13.7 GB (Q8_0).

SabbatH 2x7B is a 12.9B-parameter Sabbath model in GGUF format, quantized by Elizezen. Its trained context length is 4K tokens. The repository has 2 quant files, from 7.3 GB (Q4_0) to 13.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.3 GB 8.3 GB
Too big Get file →
Q8_013.7 GB 14.7 GB
Too big Get file →

What GPU do you need for SabbatH 2x7B?

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: the best quant that fits is Q4_0 (7.3 GB file, about 8.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.7 GB file, about 15.3 GB in use).

Which SabbatH 2x7B 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

Architecturellama
Parameters12.9B (approximate, mixture of experts)
Layers32
Trained context4,096 tokens
KV cache (fp16)128 KB per token

Source

Quantized byElizezen
FamilySabbath
Licenseapache-2.0
Downloads (HF)11
Last updated2024-04-18

Frequently asked questions about SabbatH 2x7B

How much VRAM does SabbatH 2x7B need?

About 8.9 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 SabbatH 2x7B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SabbatH 2x7B GGUF?

It depends on the quant: Q4_0 is 7.3 GB, Q8_0 is 13.7 GB.

What context length does SabbatH 2x7B support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.1 GB at 8K and 0.5 GB at 4K.

Where can I download SabbatH 2x7B GGUF?

The files are on Hugging Face in the Elizezen/SabbatH-2x7B-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 SabbatH 2x7B use?

Hugging Face lists the license as apache-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 from Elizezen

All by Elizezen →

More Sabbath models

All Sabbath →

Other medium models

All medium models →