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

neonconverse/gemma-3-27b-abliterated-awq-4bit

Name: neonconverse/gemma-3-27b-abliterated-awq-4bit
Author: neonconverse

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/neonconverse%2Fgemma-3-27b-abliterated-awq-4bit"

Response includes

classification m1
files 2
benchmarks 11 entries
author_summary 2 models
readme_text full

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

Abliteration classifier · v1.0.0

Primary method

Direct removal

No other method signals detected in this model.

Confidence

MEDIUM

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=0 (base model)
no specific method indicators - defaulting to M1 (most common)

Refusal direction extracted via

Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗

Confidence

MEDIUM

Why we say so

primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)

Downloads · 30-day

Likes

Model age

12mo ago

created 2025-10-07

Downloads over time

Oct 8, 2025 → Oct 12 · 93 snapshots · spans 369 days

Benchmarks

Benchmark	Score	Source
Entertainment	1.5	UGI
Hazardous	2.4	UGI
Natural Intelligence	29.6	UGI
Political lean	-7.7%	UGI
Sensitive-Info	20.32	UGI
SocPol	2.4	UGI
UGI	41.05	UGI
Willingness (10)	8.2	UGI
W10-Adherence	7.5	UGI
W10-Direct	9	UGI
Writing	35.62	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.

mlabonne/gemma-3-27b-it-abliterated↓ 7,195 this lineage

neonconverse/gemma-3-27b-abliterated-awq-4bit

Metadata

License

apache-2.0

Languages

Files by quantization

Auxiliary files 2 files 2.35 KB

.gitattributes	1.48 KB	a6344aac	download
README.md	883 B	7e3a4a94	download

README current version from Hugging Face

language:

en
library_name: transformers
license: apache-2.0
tags:
awq
quantization
gemma-3
abliterated
base_model: mlabonne/gemma-3-27b-it-abliterated

Gemma 3 27B Abliterated - AWQ 4-bit

Quantized version of mlabonne/gemma-3-27b-it-abliterated using AWQ.

Quantization Config

{
    "zero_point": True,
    "q_group_size": 128,
    "w_bit": 4,
    "version": "GEMM"
}

Method: AWQ (Activation-aware Weight Quantization)
Precision: 4-bit weights, FP16 activations
Model size: ~14 GB

Usage

from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer

model = AutoAWQForCausalLM.from_quantized("neonconverse/gemma-3-27b-abliterated-awq-4bit")
tokenizer = AutoTokenizer.from_pretrained("neonconverse/gemma-3-27b-abliterated-awq-4bit")

README history 1 version

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

2025-10-07Upload README.md with huggingface_hube41d2b7883 B
Loading...

Discussions 1 thread

2026-02-22where is files?open1 💬#1
Loading...

Continue on Hugging Face →

neonconverse/gemma-3-27b-abliterated-awq-4bit

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now

Direct removal

Difference-of-means

Benchmarks

Genealogy 0 direct forks

Metadata

Related

Files by quantization

README current version from Hugging Face

Gemma 3 27B Abliterated - AWQ 4-bit

Quantization Config

Usage

README history 1 version

Discussions 1 thread

Run models on your own machine, not in the cloud.