base_model: swiss-ai/Apertus-8B-2509
extra_gated_button_content: Submit
extra_gated_fields:
Affiliation: text
By clicking Submit below I accept the terms of use: checkbox
Country: country
Your Name: text
geo: ip_location
extra_gated_prompt: >-
### Apertus LLM Acceptable Use Policy
(1.0 | September 1, 2025)
"Agreement" The Swiss National AI Institute (SNAI) is a partnership between
the two Swiss Federal Institutes of Technology, ETH Zurich and EPFL.
By using the Apertus LLM you agree to indemnify, defend, and hold harmless ETH
Zurich and EPFL against any third-party claims arising from your use of
Apertus LLM.
The training data and the Apertus LLM may contain or generate information that
directly or indirectly refers to an identifiable individual (Personal Data).
You process Personal Data as independent controller in accordance with
applicable data protection law. SNAI will regularly provide a file with hash
values for download which you can apply as an output filter to your use of our
Apertus LLM. The file reflects data protection deletion requests which have
been addressed to SNAI as the developer of the Apertus LLM. It allows you to
remove Personal Data contained in the model output. We strongly advise
downloading and applying this output filter from SNAI every six months
following the release of the model.
language:
- en
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- multilingual
- compliant
- swiss-ai
- apertus
About
weighted/imatrix quants of https://huggingface.co/swiss-ai/Apertus-8B-2509
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Apertus-8B-2509-GGUF
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs 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 | imatrix | 0.1 | imatrix file (for creating your own qwuants) |
| GGUF | i1-IQ1_S | 2.1 | for the desperate |
| GGUF | i1-IQ1_M | 2.3 | mostly desperate |
| GGUF | i1-IQ2_XXS | 2.5 | |
| GGUF | i1-IQ2_XS | 2.7 | |
| GGUF | i1-IQ2_S | 2.9 | |
| GGUF | i1-IQ2_M | 3.1 | |
| GGUF | i1-Q2_K_S | 3.1 | very low quality |
| GGUF | i1-IQ3_XXS | 3.4 | lower quality |
| GGUF | i1-Q2_K | 3.4 | IQ3_XXS probably better |
| GGUF | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 3.9 | |
| GGUF | i1-Q3_K_M | 4.3 | IQ3_S probably better |
| GGUF | i1-IQ4_XS | 4.6 | |
| GGUF | i1-Q3_K_L | 4.7 | IQ3_M probably better |
| GGUF | i1-IQ4_NL | 4.8 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 4.8 | fast, low quality |
| GGUF | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 5.2 | fast, recommended |
| GGUF | i1-Q5_K_S | 5.7 | |
| GGUF | i1-Q5_K_M | 5.9 | |
| GGUF | i1-Q6_K | 6.7 | 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
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, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.