language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- moe
- merge
- mergekit
- Solar Moe
- Solar
- Umbra
About
static quants of https://huggingface.co/Steelskull/Umbra-v2.1-MoE-4x10.7
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Umbra-v2.1-MoE-4x10.7-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 | 13.4 | |
| GGUF | IQ3_XS | 14.9 | |
| GGUF | Q3_K_S | 15.8 | |
| GGUF | IQ3_S | 15.8 | fast, beats Q3_K* |
| GGUF | IQ3_M | 16.1 | |
| GGUF | Q3_K_M | 17.5 | lower quality |
| GGUF | Q3_K_L | 19.0 | |
| GGUF | IQ4_XS | 19.7 | |
| GGUF | Q4_K_S | 20.8 | fast, medium quality |
| GGUF | Q4_K_M | 22.1 | fast, medium quality |
| GGUF | Q5_K_S | 25.1 | |
| GGUF | Q5_K_M | 25.9 | |
| GGUF | Q6_K | 29.9 | very good quality |
| GGUF | Q8_0 | 38.6 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
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.