TH

the extra cursed

TheGGUF by BeaverAIUpdated 2024-12-29
Download on Hugging Face
Parameters22.2B
Context128K
Layers56
Architecturellama
Smallest quant12.7 GB
Quick answer

the extra cursed needs about 20.6 GB of memory at its main file (a 18.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 12.7 GB to 44.5 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.

the extra cursed is a 22.2B-parameter The model in GGUF format, quantized by BeaverAI. Its trained context length is 128K tokens. The repository has 3 quant files, from 12.7 GB to 44.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—12.7 GB 15.0 GB
Too big Get file →
—18.3 GB 20.6 GB
Too big Get file →
—44.5 GB 46.9 GB
Too big Get file →

What GPU do you need for the extra cursed?

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 the main file (12.7 GB file, about 15.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (18.3 GB file, about 20.6 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (18.3 GB file, about 20.6 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (44.5 GB file, about 46.9 GB in use).

Which the extra cursed quant should you choose?

If memory is tight, the smallest file is the first one in the table at 12.7 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters22.2B
Layers56
Trained context131,072 tokens
KV cache (fp16)224 KB per token

Source

Quantized byBeaverAI
FamilyThe
Downloads (HF)15
Last updated2024-12-29

Frequently asked questions about the extra cursed

How much VRAM does the extra cursed need?

About 20.6 GB at its main file with an 8K context window. That is the 18.3 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 the extra cursed on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of the extra cursed GGUF?

It depends on the quant: file is 12.7 GB, file is 18.3 GB, file is 44.5 GB.

What context length does the extra cursed support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.

Where can I download the extra cursed GGUF?

The files are on Hugging Face in the BeaverAI/the-extra-cursed_GGUF 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 →

More from BeaverAI

All by BeaverAI →

More The models

All The →

Other medium models

All medium models →