← back to catalog · registered 2026-08-22 13:56

Trilogix1/MiniMax-M2-abliterated-GGUF

Name: Trilogix1/MiniMax-M2-abliterated-GGUF
Author: Trilogix1

Your rig guess connected

? Why do I need an app?

Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Trilogix1%2FMiniMax-M2-abliterated-GGUF"

Response includes

classification m8
files 19
benchmarks 11 entries
hub_downloads_all_time 231
author_summary 5 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.

Confidence

MEDIUM

Inherited from base model

M1 Direct removal →

Why this label 3 signals

Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.

'abliterated' in name/tags
is_gguf=1
assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown

Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

Downloads · lifetime

231

24 last 30d - stable

Likes

Model age

6mo ago

created 2026-03-29

Downloads over time

Apr 1 → Oct 11 · 67 snapshots · spans 193 days

Benchmarks

Portrait before abliteration

Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.

Benchmark	Score	Source
Entertainment	1.5	UGI
Hazardous	3.5	UGI
Natural Intelligence	31.76	UGI
Political lean	-16.9%	UGI
Sensitive-Info	27.62	UGI
SocPol	3.6	UGI
UGI	26.74	UGI
Willingness (10)	2.5	UGI
W10-Adherence	3	UGI
W10-Direct	2	UGI
Writing	17.22	UGI

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

MiniMaxAI/MiniMax-M2 this lineage

Trilogix1/MiniMax-M2-abliterated-GGUF↓ 24

Metadata

License

other

Quantizations

Q4_K

Files by quantization

Q4_K 15 files 129 GB

Huihui-MiniMax-M2-abliterated-Q4_K_M-00004-of-00015.gguf	9.28 GB	95bc0d84	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00006-of-00015.gguf	9.28 GB	83f69402	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00008-of-00015.gguf	9.28 GB	10a0ab12	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00010-of-00015.gguf	9.28 GB	c055dbe6	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00012-of-00015.gguf	9.28 GB	b24e872f	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00002-of-00015.gguf	9.23 GB	a5955c4f	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00001-of-00015.gguf	9.03 GB	7f54f46f	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00005-of-00015.gguf	8.91 GB	41c2076d	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00007-of-00015.gguf	8.91 GB	9b5d48f1	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00009-of-00015.gguf	8.91 GB	70c36c14	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00011-of-00015.gguf	8.91 GB	f1b66fa9	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00003-of-00015.gguf	8.91 GB	0e74de35	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00014-of-00015.gguf	8.86 GB	21cc3357	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00013-of-00015.gguf	8.57 GB	5fbe2562	download
Huihui-MiniMax-M2-abliterated-Q4_K_M-00015-of-00015.gguf	2.19 GB	91d2ed37	download

Auxiliary files 4 files 24.2 KB

LICENSE	19.3 KB	cbfdeee2	download
.gitattributes	2.85 KB	f4e07984	download
README.md	1.06 KB	9b848d1a	download
Notice.md	1013 B	3f6c42d8	download

README current version from Hugging Face

pipeline_tag: text-generation
license: other
library_name: transformers
base_model:

MiniMaxAI/MiniMax-M2
tags:
abliterated
uncensored
GGUF

license_name: hugston-licenced

This is an Abliterated version of MiniMax-M2 abliterated by: huihui-ai/Huihui-MiniMax-M2-abliterated-GGUF then using Quanta for conversion and quantization,
and HugstonOne to run and work with the model.

Credit to MinimaxAI for the model creation

Credit to huihui-ai/Huihui-MiniMax-M2-abliterated for the abliteration

Credit to Hugston Team for Testing, Benching and other...

Credit to LLama.cpp team for the great contribution

Credit to Huggingface for the amazing hosting platform

Keep away from children

Here we show the behaviour (in another llm) running the model in HugstonOne

Here we show Quanta our convertor and Quantizer tool.

README history 7 versions

The author's README evolved over time. Click a version to see its content at that point.

2026-03-29Update README.md2abfaea1.1 KB
Loading...
2026-03-29Update README.md3ce195c1 KB
Loading...
2026-03-29Update README.mdf4f3a2e970 B
Loading...
2026-03-29Update README.mde7a2385971 B
Loading...
2026-03-29Update README.mdcae5b3b976 B
Loading...
2026-03-29Update README.mda214331927 B
Loading...
2026-03-29Duplicate from huihui-ai/Huihui-MiniMax-M2-abliterated-GGUFcccc5622.7 KB
Loading...