← back to catalog · registered 2026-10-23 22:00

EsteefAi/gemma-3-4b-it-abliterated-v2-GGUF-mirror

EsteefAi Gemma 4B GGUF 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/EsteefAi%2Fgemma-3-4b-it-abliterated-v2-GGUF-mirror"
Response includes
  • classification m8
  • files 4
  • author_summary 5 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

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

What is a refusal direction? →
Downloads · 30-day
0
Likes
1
Model age
today
created 2026-10-23

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.

Metadata

License
gemma
Tags
gguf mirror base_model:mlabonne/gemma-3-4b-it-abliterated-v2 base_model:quantized:mlabonne/gemma-3-4b-it-abliterated-v2 license:gemma endpoints_compatible region:us conversational

Related

Total size
2.97 GB
Files
4
Quantizations
1
Registered
2026-10-23 22:00
Last updated on HF
2026-10-23 21:14

Files by quantization

Auxiliary files 4 files 2.97 GB
gemma-3-4b-it-abliterated-v2.q6_k.gguf 2.97 GB 47636d77 download
.gitattributes 1.56 KB be79bbb3 download
README.md 1.44 KB ce4d5b8b download
NOTICE 206 B 9b11ddf4 download

README current version from Hugging Face


license: gemma
base_model:

  • mlabonne/gemma-3-4b-it-abliterated-v2
    tags:
  • mirror
  • gguf

Gemma 3 4B IT abliterated v2 (GGUF) - mirror

This is a mirror, not our work. It is an unmodified copy of the file(s) Philibert uses from
mlabonne/gemma-3-4b-it-abliterated-v2-GGUF by mlabonne (abliteration) / Google (Gemma 3), kept here so that
Philibert installs keep working even if the original moves.
All credit belongs to the original authors. Please see, follow and cite the original repository,
and keep to its licence and its use policy.

File SHA-256 (same as the original)
gemma-3-4b-it-abliterated-v2.q6_k.gguf 47636d7767f26ce90e8fa8f81c33d62c81fc2cffd3f0bb7bcd4569fff02e8c7f

Philibert downloads this through Ollama (ollama pull hf.co/EsteefAi/gemma-3-4b-it-abliterated-v2-GGUF-mirror:<quant>) when the person asks for the model.

Mirrored by Esteef.Ai for Philibert. If you are the author and want this mirror changed or removed,
open a discussion on this repository.

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.

Open in Abliteration