mradermacher's picture
auto-patch README.md
a3fd11b verified
metadata
base_model: SteelStorage/Umbra-v2.1-MoE-4x10.7
language:
  - en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
  - moe
  - merge
  - mergekit
  - Solar Moe
  - Solar
  - Umbra

About

weighted/imatrix quants of https://huggingface.co/SteelStorage/Umbra-v2.1-MoE-4x10.7

static quants are available at https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-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-IQ1_S 7.7 for the desperate
GGUF i1-IQ1_M 8.5 mostly desperate
GGUF i1-IQ2_XXS 9.8
GGUF i1-IQ2_XS 10.9
GGUF i1-IQ2_S 11.1
GGUF i1-IQ2_M 12.2
GGUF i1-Q2_K 13.4 IQ3_XXS probably better
GGUF i1-IQ3_XXS 14.2 lower quality
GGUF i1-IQ3_XS 14.9
GGUF i1-Q3_K_S 15.8 IQ3_XS probably better
GGUF i1-IQ3_S 15.8 beats Q3_K*
GGUF i1-IQ3_M 16.1
GGUF i1-Q3_K_M 17.5 IQ3_S probably better
GGUF i1-Q3_K_L 19.0 IQ3_M probably better
GGUF i1-IQ4_XS 19.5
GGUF i1-Q4_0 20.7 fast, low quality
GGUF i1-Q4_K_S 20.8 optimal size/speed/quality
GGUF i1-Q4_K_M 22.1 fast, recommended
GGUF i1-Q5_K_S 25.1
GGUF i1-Q5_K_M 25.9
GGUF i1-Q6_K 29.9 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

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.