mradermacher's picture
auto-patch README.md
23e50f6 verified
metadata
base_model: jsfs11/L3-8B-Stheno-2x8B-MoE
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - moe
  - frankenmoe
  - merge
  - mergekit
  - lazymergekit
  - Sao10K/L3-8B-Stheno-v3.2
  - Sao10K/L3-8B-Stheno-v3.1
  - not-for-all-audiences

About

static quants of https://huggingface.co/jsfs11/L3-8B-Stheno-2x8B-MoE

weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3-8B-Stheno-2x8B-MoE-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 5.3
GGUF IQ3_XS 5.9
GGUF Q3_K_S 6.2
GGUF IQ3_S 6.2 beats Q3_K*
GGUF IQ3_M 6.3
GGUF Q3_K_M 6.8 lower quality
GGUF Q3_K_L 7.3
GGUF IQ4_XS 7.6
GGUF Q4_K_S 8.0 fast, recommended
GGUF Q4_K_M 8.4 fast, recommended
GGUF Q5_K_S 9.6
GGUF Q5_K_M 9.8
GGUF Q6_K 11.3 very good quality
GGUF Q8_0 14.6 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.