mradermacher's picture
auto-patch README.md
1edb21e verified
metadata
base_model: FluffyKaeloky/Luminum-v0.1-123B
language:
  - en
library_name: transformers
quantized_by: mradermacher
tags:
  - mergekit
  - merge

About

static quants of https://huggingface.co/FluffyKaeloky/Luminum-v0.1-123B

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Luminum-v0.1-123B-i1-GGUF

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 45.3
PART 1 PART 2 IQ3_XS 50.2
PART 1 PART 2 Q3_K_S 52.9
PART 1 PART 2 IQ3_S 53.1 beats Q3_K*
PART 1 PART 2 IQ3_M 55.4
PART 1 PART 2 Q3_K_M 59.2 lower quality
PART 1 PART 2 Q3_K_L 64.7
PART 1 PART 2 IQ4_XS 66.1
PART 1 PART 2 Q4_K_S 69.7 fast, recommended
PART 1 PART 2 Q4_K_M 73.3 fast, recommended
PART 1 PART 2 Q5_K_S 84.5
PART 1 PART 2 Q5_K_M 86.6
PART 1 PART 2 PART 3 Q6_K 100.7 very good quality
PART 1 PART 2 PART 3 Q8_0 130.4 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

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.

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.