README.md

metadata

base_model: darkc0de/XORTRON-NXTXPRTXXL
language:
  - en
library_name: transformers
license: apache-2.0
mradermacher:
  readme_rev: 1
quantized_by: mradermacher
tags:
  - mistral
  - mistral-3.5
  - text-only
  - bf16
  - 128b
  - heretic
  - uncensored
  - decensored
  - abliterated
  - reproducible

About

weighted/imatrix quants of https://huggingface.co/darkc0de/XORTRON-NXTXPRTXXL

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/XORTRON-NXTXPRTXXL-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 quants)
GGUF	i1-IQ1_S	27.3	for the desperate
GGUF	i1-IQ1_M	29.7	mostly desperate
GGUF	i1-IQ2_XXS	33.8
GGUF	i1-IQ2_XS	37.4
GGUF	i1-IQ2_S	39.8
GGUF	i1-IQ2_M	43.1
GGUF	i1-Q2_K_S	43.1	very low quality
GGUF	i1-Q2_K	46.7	IQ3_XXS probably better
GGUF	i1-IQ3_XXS	48.5	lower quality
GGUF	i1-IQ3_XS	51.8
GGUF	i1-Q3_K_S	54.5	IQ3_XS probably better
GGUF	i1-IQ3_S	54.6	beats Q3_K*
GGUF	i1-IQ3_M	56.9
GGUF	i1-Q3_K_M	60.7	IQ3_S probably better
GGUF	i1-Q3_K_L	66.2	IQ3_M probably better
GGUF	i1-Q4_K_S	71.3	optimal size/speed/quality
GGUF	i1-Q4_K_M	75.0	fast, recommended
GGUF	i1-Q4_1	78.6
GGUF	i1-Q5_K_S	86.3
GGUF	i1-Q5_K_M	88.4
PART 1 PART 2 PART 3	i1-Q6_K	102.7	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.