---
base_model: TheDrummer/Skyfall-36B-v2
language:
- en
license: mit
quantized_by: SpongeQuant
tags:
- SpongeQuant
- i1-GGUF
---


Quantized to `i1-GGUF` using [SpongeQuant](https://github.com/SpongeEngine/SpongeQuant), the Oobabooga of LLM quantization. Chat & support at [Sponge Engine](https://discord.gg/azNmr2Gdgy).

<figure>
  <img src="https://huggingface.co/spaces/SpongeEngine/README/resolve/main/038.png" alt="38. Family portrait">
  <figcaption>38. Family portrait</figcaption>
</figure>

<figure>
  <audio controls>
    <source src="https://huggingface.co/spaces/SpongeEngine/README/resolve/main/025.mp3" type="audio/mp3">
    Your browser does not support the audio element.
  </audio>
  <figcaption>25. The Fairie Round – Early Music Consort of London / David Munrow (Anthony Holborne)</figcaption>
</figure>

***
### What is a GGUF?
GGUF is a type of file format used for running LLMs (large language models) on different types of computers. It works on both regular processors (CPU) and graphics cards (GPU). Some LLMs need powerful and expensive hardware, but GGUF makes it possible to run them on a wider range of computers, even ones without high-end GPUs. To make this possible, GGUF models use a technique called quantization, which reduces their size and memory usage. This helps them run more efficiently, but at lower settings, the model might lose some accuracy or detail in its responses.