PiVoT-MoE-i1-GGUF / README.md
mradermacher's picture
auto-patch README.md
2aaeacc verified
|
raw
history blame
2.62 kB
metadata
exported_from: maywell/PiVoT-MoE
language:
  - en
library_name: transformers
license: cc-by-nc-4.0
quantized_by: mradermacher

About

weighted/imatrix quants of https://huggingface.co/maywell/PiVoT-MoE

static quants are available at https://huggingface.co/mradermacher/PiVoT-MoE-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 i1-IQ2_M 12.0
GGUF i1-Q2_K 13.3 IQ3_XXS probably better
GGUF i1-IQ3_XXS 14.0 lower quality
GGUF i1-Q3_K_S 15.7 IQ3_XS probably better
GGUF i1-Q3_K_M 17.4 IQ3_S probably better
GGUF i1-IQ4_XS 19.4
GGUF i1-Q4_K_S 20.6 optimal size/speed/quality
GGUF i1-Q4_K_M 21.9 fast, recommended
GGUF i1-Q6_K 29.7 practically like static Q6_K

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.