|
--- |
|
exported_from: Undi95/MXLewd-L2-20B |
|
language: |
|
- en |
|
library_name: transformers |
|
license: cc-by-nc-4.0 |
|
quantized_by: mradermacher |
|
--- |
|
## About |
|
|
|
weighted/imatrix quants of https://huggingface.co/Undi95/MXLewd-L2-20B |
|
|
|
|
|
<!-- provided-files --> |
|
## 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/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 5.7 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 6.3 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ2_S.gguf) | i1-IQ2_S | 6.7 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ2_M.gguf) | i1-IQ2_M | 7.2 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q2_K.gguf) | i1-Q2_K | 7.7 | IQ3_XXS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 7.9 | lower quality | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 8.5 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ3_S.gguf) | i1-IQ3_S | 9.0 | beats Q3_K* | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 9.0 | IQ3_XS probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ3_M.gguf) | i1-IQ3_M | 9.4 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 10.0 | IQ3_S probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 10.9 | IQ3_M probably better | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 11.0 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q4_0.gguf) | i1-Q4_0 | 11.6 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 11.7 | optimal size/speed/quality | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 12.3 | fast, recommended | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 14.1 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 14.5 | | |
|
| [GGUF](https://huggingface.co/mradermacher/MXLewd-L2-20B-i1-GGUF/resolve/main/MXLewd-L2-20B.i1-Q6_K.gguf) | i1-Q6_K | 16.7 | practically like static Q6_K | |
|
|
|
|
|
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](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 --> |
|
|
