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

altomek/Gemma-4-31B-it-Abliterated-XXL-GGUF

altomek Gemma 31B GGUF multimodal second-order 262K ctx
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/altomek%2FGemma-4-31B-it-Abliterated-XXL-GGUF"
Response includes
  • classification m8
  • files 4
  • hub_downloads_all_time 1,396
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=altomek
All 2 models by altomek
 GET/models?family=gemma&method=m8
Sibling gemma models · same method
 GET/methods/m8
What "m8" means · taxonomy
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
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
How we label → About M8 →
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
1K
104 last 30d - cooling
Likes
0
Model age
6mo ago
created 2026-04-12
Downloads over time
Now1.4K→from692↑106%
6559361.2K1.5K692 on Apr 151.4K on Oct 121.4K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 12 · 66 snapshots · spans 180 days

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.

null-space/gemma-4-31b-it-abliterated↓ 90 this lineage
altomek/Gemma-4-31B-it-Abliterated-XXL-GGUF↓ 104

Metadata

License
apache-2.0
Languages
en
Quantizations
Q4_K
Tags
transformers gguf abliterated uncensored gemma4 gemma multimodal ablation image-text-to-text en base_model:null-space/gemma-4-31b-it-abliterated base_model:quantized:null-space/gemma-4-31b-it-abliterated

Related

Other by altomek
WizardLM-33B-V1.0-Uncensored-GGUF 64
Same base model
divinetribe/gemma-4-31b-it-abliterated-4bit-mlx 620 aacidburn/null-space-gemma-4-31b-it-abliterated-GGUF 45
Total size
21.1 GB
Files
4
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-04-12 22:54
Source huggingface.co/altomek/Gemma-4-31B-it-Abliterated-XXL-GGUF ↗ Base model null-space/gemma-4-31b-it-abliterated →

Files by quantization

Q4_K 1 file 21.1 GB
Gemma-4-31B-it-Abliterated-Q4_K_XXL.gguf 21.1 GB 5de4accc download
BF16 1 file 1.12 GB
Gemma-4-31B-it-Abliterated-mmproj-BF16.gguf 1.12 GB 78d2a071 download
Auxiliary files 2 files 2.21 KB
.gitattributes 1.64 KB ee222890 download
README.md 586 B 835757cd download

README current version from Hugging Face

license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
base_model:

  • null-space/gemma-4-31b-it-abliterated
    tags:
  • abliterated
  • uncensored
  • gemma4
  • gemma
  • multimodal
  • ablation
    language:
  • en
    library_name: transformers
    pipeline_tag: image-text-to-text
    model-index:
  • name: gemma-4-31b-it-abliterated
    results: []

Gemma-4-31B-IT-Abliterated

XXL GGUF quant of https://huggingface.co/null-space/gemma-4-31b-it-abliterated

Changelog:

  • reupload with BOS token, new chat template
  • reupload with new tokenizer_config.json...

README history 1 version

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

  1. 2026-04-12Create README.mde4b848c586 B
    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