|
|
--- |
|
|
base_model: armand0e/gpt-oss-20b-glm-4.6-distill |
|
|
datasets: |
|
|
- Liontix/glm-4.6-250x |
|
|
language: |
|
|
- en |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
mradermacher: |
|
|
readme_rev: 1 |
|
|
quantized_by: mradermacher |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- gpt_oss |
|
|
--- |
|
|
## About |
|
|
|
|
|
<!-- ### quantize_version: 2 --> |
|
|
<!-- ### output_tensor_quantised: 1 --> |
|
|
<!-- ### convert_type: hf --> |
|
|
<!-- ### vocab_type: --> |
|
|
<!-- ### tags: nicoboss --> |
|
|
<!-- ### quants: MXFP4_MOE Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> |
|
|
<!-- ### quants_skip: --> |
|
|
<!-- ### skip_mmproj: --> |
|
|
weighted/imatrix quants of https://huggingface.co/armand0e/gpt-oss-20b-glm-4.6-distill |
|
|
|
|
|
<!-- provided-files --> |
|
|
|
|
|
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-20b-glm-4.6-distill-i1-GGUF).*** |
|
|
|
|
|
static quants are available at https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-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/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own qwuants) | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality | |
|
|
| [GGUF](https://huggingface.co/mradermacher/gpt-oss-20b-glm-4.6-distill-i1-GGUF/resolve/main/gpt-oss-20b-glm-4.6-distill.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended | |
|
|
|
|
|
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. Additional thanks to [@nicoboss](https://huggingface.co/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. |
|
|
|
|
|
<!-- end --> |
|
|
|
