---
language:
- en
library_name: transformers
license: llama2
quantized_by: mradermacher
tags:
- moe
---
## About

static quants of https://huggingface.co/ibivibiv/orthorus-125b-moe

<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/orthorus-125b-moe-i1-GGUF
## Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) 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](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q2_K.gguf) | Q2_K | 46.8 |  |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_XS.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_XS.gguf.split-ab) | Q3_K_XS | 51.6 |  |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_S.gguf.split-ab) | Q3_K_S | 55.1 |  |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_M.gguf.split-ab) | Q3_K_M | 61.1 | lower quality |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q3_K_L.gguf.split-ab) | Q3_K_L | 66.1 |  |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q4_K_S.gguf.split-ab) | Q4_K_S | 72.2 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q4_K_M.gguf.split-ab) | Q4_K_M | 76.5 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q5_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q5_K_S.gguf.split-ab) | Q5_K_S | 87.2 |  |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q5_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q5_K_M.gguf.split-ab) | Q5_K_M | 89.7 |  |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q6_K.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q6_K.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q6_K.gguf.split-ac) | Q6_K | 103.8 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q8_0.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q8_0.gguf.split-ab) [PART 3](https://huggingface.co/mradermacher/orthorus-125b-moe-GGUF/resolve/main/orthorus-125b-moe.Q8_0.gguf.split-ac) | Q8_0 | 134.1 | fast, best quality |


Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

## Thanks

I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

<!-- end -->