base_model: helixdouble/GLM-5.1-Abliterated language:
- en
- zh library_name: transformers license: agpl-3.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags:
- abliterated
- uncensored
- moe
- glm
- glm-5.1
- fp8
- blackwell
About
weighted/imatrix quants of https://huggingface.co/helixdouble/GLM-5.1-Abliterated
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/GLM-5.1-Abliterated-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 | 1.2 | imatrix file (for creating your own quants) |
| P1 P2 P3 P4 P5 P6 | i1-Q2_K | 274.3 | IQ3_XXS probably better |
| P1 P2 P3 P4 P5 P6 P7 | i1-IQ3_S | 324.9 | beats Q3_K* |
| P1 P2 P3 P4 P5 P6 P7 | i1-Q3_K_S | 324.9 | IQ3_XS probably better |
| P1 P2 P3 P4 P5 P6 P7 | i1-IQ3_M | 328.6 | |
| P1 P2 P3 P4 P5 P6 P7 P8 | i1-Q3_K_M | 359.1 | IQ3_S probably better |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 | i1-Q3_K_L | 390.4 | IQ3_M probably better |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 | i1-IQ4_XS | 401.3 | |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 | i1-Q4_0 | 426.0 | fast, low quality |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 | i1-Q4_K_S | 427.3 | optimal size/speed/quality |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 | i1-Q4_K_M | 455.0 | fast, recommended |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 | i1-Q4_1 | 471.9 | |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 | i1-Q5_K_S | 518.9 | |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 | i1-Q5_K_M | 534.4 | |
| P1 P2 P3 P4 P5 P6 P7 P8 P9 P10 P11 P12 P13 | i1-Q6_K | 619.0 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
image.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, 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.