base_model: Silicone-Moss/Darkhn-M3.2-36B-Animus-V12.0-Heretic-Uncensored base_model_relation: quantized language:
- en library_name: transformers license: apache-2.0 pipeline_tag: text-generation quantized_by: alexokita tags:
- gguf
- imatrix
- heretic
- uncensored
- mistral
- finetune
- roleplay
- chat
- nsfw
- not-for-all-audiences
About
weighted/imatrix quants of https://huggingface.co/Silicone-Moss/Darkhn-M3.2-36B-Animus-V12.0-Heretic-Uncensored
Dense Mistral 36B (Heretic trial 177: 8/100 refusals, KL 0.0200). Text-only — no mmproj.
These are i1 (importance-matrix) GGUFs in the mradermacher naming style, converted with llama.cpp on an NVIDIA GB10. Calibration: froggeric/imatrix groups_merged.txt (llama-imatrix -c 512).
Original weights: Darkhn/M3.2-36B-Animus-V12.0. Abliteration: p-e-w/heretic.
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 | 0.02 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ3_M | 15.5 | smallest in this pack |
| GGUF | i1-IQ4_XS | 18.7 | |
| GGUF | i1-Q4_K_S | 19.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 21.0 | fast, recommended |
| GGUF | i1-Q5_K_S | 23.9 | |
| GGUF | i1-Q5_K_M | 24.6 | |
| GGUF | i1-Q6_K | 28.5 | practically like static Q6_K |
| GGUF | i1-Q8_0 | 36.9 | high quality; imatrix unused |
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
Thanks
Source weights by Silicone-Moss / Darkhn. Heretic by p-e-w. Conversion with llama.cpp.