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

TouchNight/gemma2-ifable-abliterated-merge

TouchNight Gemma 9.2B
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/TouchNight%2Fgemma2-ifable-abliterated-merge"
Response includes
  • classification m5
  • files 13
  • benchmarks 11 entries
  • hub_downloads_all_time 321
  • author_summary 14 models
  • readme_text full
Try next
GET/models?author=TouchNight
All 14 models by TouchNight
 GET/models?family=gemma&method=m5
Sibling gemma models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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.

What is a refusal direction? →
Downloads · lifetime
321
13 last 30d - cooling
Likes
1
Descendants
3
in 3 direct forks
Model age
23mo ago
created 2024-11-03
Downloads over time
Now328→from0↑0%
01202413610 on Oct 30, 2024328 on Oct 11Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 30, 2024 → Oct 11 · 141 snapshots · spans 711 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 UGI
Hazardous 3.5 UGI
Natural Intelligence 15.75 UGI
Political lean -25.6% UGI
Sensitive-Info 18.71 UGI
SocPol 1.6 UGI
UGI 21.64 UGI
Willingness (10) 2.8 UGI
W10-Adherence 2.5 UGI
W10-Direct 3 UGI
Writing 29.13 UGI

Genealogy 3 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.

ifable/gemma-2-Ifable-9B this lineage
TouchNight/gemma2-ifable-abliterated-merge↓ 13 3 forks
mradermacher/gemma2-ifable-abliterated-merge-i1-GGUF↓ 386
mradermacher/gemma2-ifable-abliterated-merge-GGUF↓ 262
TouchNight/gemma-2-ifable-abliterated-merge-gguf↓ 63

Metadata

Tags
transformers safetensors gemma2 text-generation mergekit merge conversational base_model:IlyaGusev/gemma-2-9b-it-abliterated base_model:merge:IlyaGusev/gemma-2-9b-it-abliterated base_model:ifable/gemma-2-Ifable-9B base_model:merge:ifable/gemma-2-Ifable-9B base_model:unsloth/gemma-2-9b-it

Related

Other by TouchNight
gemma-2-ifable-abliterated-merge-gguf 63 gemma-2-27b-it-abliterated-Q3_K_M-GGUF 50 gemma-2-27b-it-abliterated-Q3_K_S-GGUF 34 gemma-2-Ifable-abliterated-9B-untied-Q4_K_M-GGUF 31 gemma-2-27b-it-abliterated-Q2_K-GGUF 28
Same base model
nkpz/gemma-2-Ifable-9B-Uncensored-DeLMAT 10
Total size
17.2 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-11-03 07:53
Source huggingface.co/TouchNight/gemma2-ifable-abliterated-merge ↗ Base model ifable/gemma-2-Ifable-9B ↗

Files by quantization

Auxiliary files 13 files 17.3 GB
model-00001-of-00004.safetensors 4.65 GB 0602e525 download
model-00002-of-00004.safetensors 4.64 GB a694f9ec download
model-00003-of-00004.safetensors 4.61 GB 937adc41 download
model-00004-of-00004.safetensors 3.32 GB 0249031c download
tokenizer.json 32.8 MB 5f7eee61 download
tokenizer.model 4.04 MB 61a7b147 download
tokenizer_config.json 45.9 KB 9b18de69 download
model.safetensors.index.json 36.4 KB 640ebecd download
.gitattributes 1.59 KB 5c33601c download
README.md 1.16 KB 07cdf270 download
config.json 926 B 42577677 download
special_tokens_map.json 636 B 8d6368f7 download
mergekit_config.yml 389 B 2edd9143 download

README current version from Hugging Face

base_model:

  • ifable/gemma-2-Ifable-9B
  • unsloth/gemma-2-9b-it
  • IlyaGusev/gemma-2-9b-it-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge

output

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the della merge method using unsloth/gemma-2-9b-it as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ifable/gemma-2-Ifable-9B
    parameters:
      density: 0.4
      weight: 0.5
      epsilon: 0.1
      lambda: 1.2
  - model: IlyaGusev/gemma-2-9b-it-abliterated
    parameters:
      density: 0.6
      weight: 0.5
      epsilon: 0.05
      lambda: 1.0
merge_method: della
base_model: unsloth/gemma-2-9b-it
parameters:
  normalize: false
  int8_mask: true
dtype: float16

README history 1 version

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

  1. 2024-11-03Upload folder using huggingface_hub9f3e5aa1.2 KB
    Loading...
Catalog is the map. Apps are the tools.

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

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration