AB

AbominationScience 12B v4

AbominationscienceGGUF by KhettermanUpdated 2024-11-20
Download on Hugging Face
Parameters12.2B
Context1000K
Layers40
Architecturellama
Smallest quant7.1 GB
Quick answer

AbominationScience 12B v4 needs about 11.9 GB of memory at Q6_K (a 10.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 7.1 GB (Q4_0) to 13.0 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

AbominationScience 12B v4 is a 12.2B-parameter Abominationscience model in GGUF format, quantized by Khetterman. Its trained context length is 1000K tokens. The repository has 3 quant files, from 7.1 GB (Q4_0) to 13.0 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_07.1 GB 8.9 GB
Too big Get file →
Q6_K10.1 GB 11.9 GB
Too big Get file →
Q8_013.0 GB 14.9 GB
Too big Get file →

What GPU do you need for AbominationScience 12B v4?

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 Q6_K (10.1 GB file, about 11.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).

Which AbominationScience 12B v4 quant should you choose?

Q6_K (10.1 GB) is the middle option in this repository. Very close to the original quality for most uses, at a clearly larger size than 4-bit.

If memory is tight, the smallest file is Q4_0 at 7.1 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
Parameters12.2B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized byKhetterman
Downloads (HF)59
Last updated2024-11-20

Frequently asked questions about AbominationScience 12B v4

How much VRAM does AbominationScience 12B v4 need?

About 11.9 GB at Q6_K with an 8K context window. That is the 10.1 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 AbominationScience 12B v4 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 AbominationScience 12B v4 GGUF?

It depends on the quant: Q4_0 is 7.1 GB, Q6_K is 10.1 GB, Q8_0 is 13.0 GB.

What context length does AbominationScience 12B v4 support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download AbominationScience 12B v4 GGUF?

The files are on Hugging Face in the Khetterman/AbominationScience-12B-v4-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of AbominationScience-12B-v4

Similar models

Browse all →

More from Khetterman

All by Khetterman →

More Abominationscience models

All Abominationscience →

Other medium models

All medium models →