mradermacher's picture
auto-patch README.md
07d5a4e verified
metadata
base_model: Steelskull/Umbra-v3-MoE-4x11b-2ex
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - moe
  - frankenmoe
  - merge
  - mergekit
  - Himitsui/Kaiju-11B
  - Sao10K/Fimbulvetr-11B-v2
  - decapoda-research/Antares-11b-v2
  - beberik/Nyxene-v3-11B

About

static quants of https://huggingface.co/Steelskull/Umbra-v3-MoE-4x11b-2ex

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Umbra-v3-MoE-4x11b-2ex-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 13.3
GGUF IQ3_XS 14.9
GGUF Q3_K_S 15.7
GGUF IQ3_S 15.7 beats Q3_K*
GGUF IQ3_M 16.0
GGUF Q3_K_M 17.4 lower quality
GGUF Q3_K_L 18.8
GGUF IQ4_XS 19.6
GGUF Q4_K_S 20.6 fast, recommended
GGUF Q4_K_M 21.9 fast, recommended
GGUF Q5_K_S 24.9
GGUF Q5_K_M 25.7
GGUF Q6_K 29.7 very good quality
GGUF Q8_0 38.5 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.