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

Weighted imatrix quantize of https://huggingface.co/sophosympatheia/Midnight-Rose-103B-v2.0.3

The weight was calculated using an experimental (potentially crappy) method that is iterative (thus the "i1"), using 270k semi-random english tokens.

<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-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/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 |  |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 |  |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q2_K.gguf) | i1-Q2_K | 38.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 40.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_XS.gguf) | i1-Q3_K_XS | 42.4 |  |
| [GGUF](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_S.gguf) | i1-Q3_K_S | 44.9 | IQ3_XS probably better |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_M.gguf.split-ab) | i1-Q3_K_M | 50.0 | IQ3_S probably better |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q3_K_L.gguf.split-ab) | i1-Q3_K_L | 54.5 | IQ3_M probably better |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_S.gguf.split-ab) | i1-Q4_K_S | 59.0 | optimal size/speed/quality |
| [PART 1](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-aa) [PART 2](https://huggingface.co/mradermacher/Midnight-Rose-103B-v2.0.3-i1-GGUF/resolve/main/Midnight-Rose-103B-v2.0.3.i1-Q4_K_M.gguf.split-ab) | i1-Q4_K_M | 62.3 | fast, recommended |


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 -->