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

Kanjdoes/Gemma3-1B-it-AbliterationMess

Kanjdoes Gemma 1000M second-order
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/Kanjdoes%2FGemma3-1B-it-AbliterationMess"
Response includes
  • classification m5
  • files 10
  • hub_downloads_all_time 102
  • author_summary 1 models
  • readme_text full
Try next
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

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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • no abliteration marker
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
102
18 last 30d - stable
Likes
1
Descendants
1
in 1 direct fork
Model age
10mo ago
created 2025-11-23
Downloads over time
Now110→from25↑340%
21538611925 on Nov 26, 2025110 on Oct 11Nov '25JanMarMayJulSep
Nov 26, 2025 → Oct 11 · 85 snapshots · spans 319 days

Genealogy 1 direct fork

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-3-1b-it-abliterated-v2↓ 115 this lineage
Kanjdoes/Gemma3-1B-it-AbliterationMess↓ 18 1 fork
mradermacher/Gemma3-1B-it-AbliterationMess-GGUF↓ 326

Metadata

Tags
transformers safetensors gemma3_text text-generation mergekit merge not-for-all-audiences base_model:DavidAU/gemma-3-1b-it-heretic-abliterated-uncensored base_model:merge:DavidAU/gemma-3-1b-it-heretic-abliterated-uncensored base_model:Novaciano/Heretic_Fusion-Gemma3-1B base_model:merge:Novaciano/Heretic_Fusion-Gemma3-1B base_model:mlabonne/gemma-3-1b-it-abliterated-v2

Related

Same base model
mradermacher/gemma-3-1b-it-abliterated-v2-GGUF 423 DevQuasar/mlabonne.gemma-3-1b-it-abliterated-v2-GGUF 325 Novaciano/Amoral_Abliterated-Gemma3-1B 18
Total size
1.86 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-11-23 09:48
Source huggingface.co/Kanjdoes/Gemma3-1B-it-AbliterationMess ↗ Base model mlabonne/gemma-3-1b-it-abliterated-v2 →

Files by quantization

Auxiliary files 10 files 1.90 GB
model.safetensors 1.86 GB b9c7137f download
tokenizer.json 31.8 MB d7864051 download
tokenizer.model 4.47 MB 1299c11d download
tokenizer_config.json 1.15 MB 2cfe89ab download
config.json 1.78 KB c89b4039 download
README.md 1.55 KB b9d379f9 download
.gitattributes 1.53 KB 52373fe2 download
special_tokens_map.json 695 B 6728103d download
mergekit_config.yml 276 B d4b3e629 download
added_tokens.json 38.0 B f9f1f4f5 download

README current version from Hugging Face

base_model:

  • mlabonne/gemma-3-1b-it-abliterated-v2
  • DavidAU/gemma-3-1b-it-heretic-abliterated-uncensored
  • Novaciano/Heretic_Fusion-Gemma3-1B
    library_name: transformers
    tags:
  • mergekit
  • merge
  • not-for-all-audiences

Gemma3-1B-it-AbliterationMess

An experimental 3-way merge of abliterated Gemma 3 1B models, created to test my mergekit setup.

Merge Details

This model is a merge of the following models using mergekit:

Configuration

The following YAML configuration was used to produce this mess:

models:
  - model: Novaciano/Heretic_Fusion-Gemma3-1B
  - model: DavidAU/gemma-3-1b-it-heretic-abliterated-uncensored
  - model: mlabonne/gemma-3-1b-it-abliterated-v2
merge_method: model_stock
base_model: Novaciano/Heretic_Fusion-Gemma3-1B
dtype: float16
parameters:
  t: 0.5

Usage

This is a raw FP16 safetensors merge. GGUF quantizations are needed for "practical" uses.

If you'd like to quantize this model, please feel free to do so!

Notes

  • Created on mobile (Termux + mergekit)
  • Untested – experimental merge
  • Should inherit reduced refusals from abliterated source models

(Un)Intended Use

Not intended for factual or safety-critical applications.

README history 3 versions

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

  1. 2025-11-23Update README.mdf6ceb751.6 KB
    Loading...
  2. 2025-11-23Update README.mdb6a274e1.5 KB
    Loading...
  3. 2025-11-23Upload folder using huggingface_hubf27d0a81.5 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