mradermacher's picture
auto-patch README.md
01ab035 verified
---
base_model: MarsupialAI/Melusine_103b
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- rp
- erp
- chat
- miqu
---
## About
weighted/imatrix quants of https://huggingface.co/MarsupialAI/Melusine_103b
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Melusine_103b-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/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ1_S.gguf) | i1-IQ1_S | 22.1 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ1_M.gguf) | i1-IQ1_M | 24.2 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 27.7 | |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 30.8 | |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ2_S.gguf) | i1-IQ2_S | 32.3 | |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ2_M.gguf) | i1-IQ2_M | 35.1 | |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q2_K.gguf) | i1-Q2_K | 38.3 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 40.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 42.6 | |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 44.9 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ3_S.gguf) | i1-IQ3_S | 45.0 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ3_M.gguf) | i1-IQ3_M | 46.5 | |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q3_K_M.gguf.part2of2) | i1-Q3_K_M | 50.0 | IQ3_S probably better |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q3_K_L.gguf.part2of2) | i1-Q3_K_L | 54.5 | IQ3_M probably better |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-IQ4_XS.gguf.part2of2) | i1-IQ4_XS | 55.5 | |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q4_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q4_0.gguf.part2of2) | i1-Q4_0 | 58.8 | fast, low quality |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q4_K_S.gguf.part2of2) | i1-Q4_K_S | 59.0 | optimal size/speed/quality |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q4_K_M.gguf.part2of2) | i1-Q4_K_M | 62.3 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 71.4 | |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 73.3 | |
| [PART 1](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Melusine_103b-i1-GGUF/resolve/main/Melusine_103b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 85.1 | practically like static Q6_K |
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
## 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](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 -->