|
|
--- |
|
|
base_model: huihui-ai/Huihui-gpt-oss-120b-mxfp4-abliterated |
|
|
language: |
|
|
- en |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
mradermacher: |
|
|
readme_rev: 1 |
|
|
quantized_by: mradermacher |
|
|
tags: |
|
|
- vllm |
|
|
- unsloth |
|
|
- abliterated |
|
|
- uncensored |
|
|
--- |
|
|
## About |
|
|
|
|
|
<!-- ### quantize_version: 2 --> |
|
|
<!-- ### output_tensor_quantised: 1 --> |
|
|
<!-- ### convert_type: hf --> |
|
|
<!-- ### vocab_type: --> |
|
|
<!-- ### tags: --> |
|
|
<!-- ### quants: MXFP4_MOE x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> |
|
|
<!-- ### quants_skip: --> |
|
|
<!-- ### skip_mmproj: --> |
|
|
static quants of https://huggingface.co/huihui-ai/Huihui-gpt-oss-120b-mxfp4-abliterated |
|
|
|
|
|
<!-- provided-files --> |
|
|
|
|
|
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF).*** |
|
|
|
|
|
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-i1-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 | |
|
|
|:-----|:-----|--------:|:------| |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q3_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q3_K_S.gguf.part2of2) | Q3_K_S | 66.2 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q2_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q2_K.gguf.part2of2) | Q2_K | 66.3 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.IQ4_XS.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.IQ4_XS.gguf.part2of2) | IQ4_XS | 67.1 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q3_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q3_K_M.gguf.part2of2) | Q3_K_M | 71.2 | lower quality | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q3_K_L.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q3_K_L.gguf.part2of2) | Q3_K_L | 73.5 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q4_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q4_K_S.gguf.part2of2) | Q4_K_S | 81.0 | fast, recommended | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q4_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q4_K_M.gguf.part2of2) | Q4_K_M | 88.0 | fast, recommended | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q5_K_S.gguf.part2of2) | Q5_K_S | 88.1 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q5_K_M.gguf.part2of2) | Q5_K_M | 94.0 | | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q6_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q6_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q6_K.gguf.part3of3) | Q6_K | 124.3 | very good quality | |
|
|
| [PART 1](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q8_0.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q8_0.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Huihui-gpt-oss-120b-mxfp4-abliterated-GGUF/resolve/main/Huihui-gpt-oss-120b-mxfp4-abliterated.Q8_0.gguf.part3of3) | Q8_0 | 124.4 | fast, best quality | |
|
|
|
|
|
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](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 --> |
|
|
|
