Melusine_103b-GGUF / README.md
mradermacher's picture
auto-patch README.md
f2ee9af verified
|
raw
history blame
3.69 kB
metadata
exported_from: MarsupialAI/Melusine_103b
language:
  - en
library_name: transformers
quantized_by: mradermacher
tags:
  - rp
  - erp
  - chat
  - miqu

About

static quants of https://huggingface.co/MarsupialAI/Melusine_103b

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF Q2_K 38.3
GGUF Q3_K_S 44.9
GGUF IQ3_S 45.0 beats Q3_K*
PART 1 PART 2 Q3_K_M 50.0 lower quality
PART 1 PART 2 Q3_K_L 54.5
PART 1 PART 2 Q4_0 58.5 fast, low quality
PART 1 PART 2 Q4_K_S 59.0 fast, recommended
PART 1 PART 2 Q4_K_M 62.3 fast, recommended
PART 1 PART 2 Q6_K 85.1 very good quality
PART 1 PART 2 PART 3 Q8_0 110.0 fast, best quality

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

image.png

And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

Thanks

I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.