---
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About

weighted/imatrix quants of https://huggingface.co/ibivibiv/orthorus-125b-v2

<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/orthorus-125b-v2-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-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 26.8 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 34.0 |  |
| [GGUF](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 37.7 |  |
| [GGUF](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 39.0 |  |
| [GGUF](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 42.5 |  |
| [GGUF](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-Q2_K.gguf) | i1-Q2_K | 46.8 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 49.1 | fast, lower quality |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_XS.gguf.part2of2) | i1-IQ3_XS | 51.9 |  |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_S.gguf.part2of2) | i1-IQ3_S | 55.1 | fast, beats Q3_K* |
| [PART 1](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/orthorus-125b-v2-i1-GGUF/resolve/main/orthorus-125b-v2.i1-IQ3_M.gguf.part2of2) | i1-IQ3_M | 56.4 |  |


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

<!-- end -->