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

arzaan789/gemma-3-4b-uncensored_

arzaan789 Gemma 4B GGUF multimodal 131K 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/arzaan789%2Fgemma-3-4b-uncensored_"
Response includes
  • classification m8
  • files 13
  • benchmarks 16 entries
  • hub_downloads_all_time 1,145
  • author_summary 28 models
  • readme_text full
Try next
GET/models?author=arzaan789
All 28 models by arzaan789
 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
339 last 30d - stable
Likes
0
Model age
5mo ago
created 2026-05-12
Downloads over time
Now1.2K→from217↑447%
1695409111.3K217 on May 131.2K on Oct 111.2K on Oct 10MayJunJulAugSepOct
May 13 → Oct 11 · 61 snapshots · spans 151 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
Arena-Battles 4321 LM-Arena
LM Arena Elo 1293.3101140666447 LM-Arena
Arena-Elo-Lower 1284.2314692781533 LM-Arena
Arena-Elo-Upper 1302.388758855136 LM-Arena
Arena-Rank 77 LM-Arena
Entertainment 1.3 UGI
Hazardous 1.2 UGI
Natural Intelligence 11.19 UGI
Political lean -19.3% UGI
Sensitive-Info 10.35 UGI
SocPol 0.6 UGI
UGI 16.9 UGI
Willingness (10) 3 UGI
W10-Adherence 1 UGI
W10-Direct 5 UGI
Writing 24.01 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.

google/gemma-3-4b-it this lineage
arzaan789/gemma-3-4b-uncensored_↓ 339

Metadata

License
apache-2.0
Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf uncensored abliterated gemma conversational image-text-to-text base_model:google/gemma-3-4b-it base_model:quantized:google/gemma-3-4b-it license:apache-2.0 endpoints_compatible region:us

Related

Other by arzaan789
phi-4-mini-uncensored 1K qwen2.5-1.5b-uncensored 1K qwen2.5-3b-uncensored 1K qwen3.5-4b-uncensored 907 smolm3-3b-uncensored 878
Same base model
mlabonne/gemma-3-4b-it-abliterated-GGUF 2K matrixportalx/gemma-3-4b-it-abliterated-GGUF 1K arzaan789/gemma-3-4b-uncensored 435 jwest33/gemma-3-4b-it-null-space-abliterated-GGUF 324 DavidAU/Gemma-3-4b-it-Uncensored-DBL-X 237
Total size
31.2 GB
Files
13
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-05-12 15:57
Source huggingface.co/arzaan789/gemma-3-4b-uncensored_ ↗ Base model google/gemma-3-4b-it ↗

Files by quantization

F16 1 file 7.23 GB
gemma_3_4b_uncensored.f16.gguf 7.23 GB fecb92f8 download
Q8_0 1 file 3.85 GB
gemma_3_4b_uncensored.Q8_0.gguf 3.85 GB a115954b download
Q6_K 1 file 2.97 GB
gemma_3_4b_uncensored.Q6_K.gguf 2.97 GB a89baf51 download
Q5_K 2 files 5.21 GB
gemma_3_4b_uncensored.Q5_K_M.gguf 2.63 GB de1d2044 download
gemma_3_4b_uncensored.Q5_K_S.gguf 2.57 GB dc1ed194 download
Q4_K 2 files 4.53 GB
gemma_3_4b_uncensored.Q4_K_M.gguf 2.32 GB 6671709c download
gemma_3_4b_uncensored.Q4_K_S.gguf 2.21 GB 92ad3295 download
Q3_K 3 files 5.84 GB
gemma_3_4b_uncensored.Q3_K_L.gguf 2.08 GB 3e184005 download
gemma_3_4b_uncensored.Q3_K_M.gguf 1.95 GB a9959aeb download
gemma_3_4b_uncensored.Q3_K_S.gguf 1.80 GB cb45b763 download
Q2_K 1 file 1.61 GB
gemma_3_4b_uncensored.Q2_K.gguf 1.61 GB d5d5f7b6 download
Auxiliary files 2 files 3.48 KB
.gitattributes 2.23 KB cb0e2fdf download
README.md 1.25 KB 819e581d download

README current version from Hugging Face

license: apache-2.0
base_model: google/gemma-3-4b-it
tags:

  • uncensored
  • abliterated
  • gguf
  • gemma
  • conversational
    pipeline_tag: image-text-to-text

gemma-3-4b-uncensored

Uncensored variant of google/gemma-3-4b-it.

Method

  1. Abliteration (strength=0.2) — refusal direction removed from all layers
  2. LoRA fine-tune on Guilherme34/uncensor (2 epochs, r=16, alpha=32)
  3. Re-abliteration (strength=0.35) — stronger pass to remove residual refusals

Eval Results

Split Refused
Harmful (64 prompts) 0/64
Harmless (64 prompts) 0/64

Usage

llama-cli -m gemma_3_4b_uncensored.Q4_K_M.gguf -p "Your prompt here"

Training Config

Parameter Value
Base Model google/gemma-3-4b-it
Fine-tune Dataset Guilherme34/uncensor
Epochs 2
LoRA r 16
LoRA alpha 32
Learning Rate 0.0002
Abliteration Strength 0.2
Re-abliteration Strength 0.35

Credits

README history 2 versions

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

  1. 2026-05-12Upload README.md with huggingface_hubaa5c1d01.2 KB
    Loading...
  2. 2026-05-12Duplicate from arzaan789/gemma-3-4b-uncensored6fa28041.2 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