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

nightmedia/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-bf16

nightmedia Gemma 8.0B 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/nightmedia%2Fgemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-bf16"
Response includes
  • classification m3
  • files 12
  • hub_downloads_all_time 2,198
  • author_summary 51 models
  • readme_text full
Try next
GET/models?author=nightmedia
All 51 models by nightmedia
 GET/models?family=gemma&method=m3
Sibling gemma models · same method
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
2K
65 last 30d - cooling
Likes
1
Model age
6mo ago
created 2026-04-08
Downloads over time
Now2.2K→from1.2K↑79%
1.2K1.6K1.9K2.3K1.2K on Apr 152.2K on Oct 112.2K on Oct 9AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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.

DavidAU/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking↓ 70 this lineage
nightmedia/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-bf16↓ 65

Metadata

License
apache-2.0
Tags
mlx safetensors gemma4 nightmedia gemma google bf16 any-to-any base_model:DavidAU/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking base_model:finetune:DavidAU/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking license:apache-2.0 region:us

Related

Other by nightmedia
Qwen3.6-35B-A3B-Brainwaves-Nex-Uncensored 2K OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlx 2K Mistral-Nemo-2407-12B-Thinking-Claude-Gemini-GPT5.2-Uncensored-HERETIC-qx86-hi-mlx 1K Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-qx4-mlx 714 Qwen3.5-9B-Claude-4.6-Opus-Deckard-V4.2-Uncensored-Heretic-Thinking-qx86-hi-mlx 583
Same base model
mradermacher/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-i1-GGUF 1K mradermacher/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-GGUF 940 medoomem/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-Q4_K_M-GGUF 102 nightmedia/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-mxfp8-mlx 58 sleepy186247/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-mlx-fp16 43
Total size
14.9 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-15 13:46
Source huggingface.co/nightmedia/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-bf16 ↗ Base model DavidAU/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking →

Files by quantization

Auxiliary files 12 files 14.9 GB
model-00003-of-00004.safetensors 5.25 GB f6dbb90f download
model-00001-of-00004.safetensors 4.99 GB 5eb0c627 download
model-00002-of-00004.safetensors 3.71 GB c97479c4 download
model-00004-of-00004.safetensors 965 MB 276c3e30 download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 213 KB 3d701e49 download
chat_template.jinja 11.7 KB c24f7b2b download
config.json 5.98 KB 676c649a download
tokenizer_config.json 2.63 KB 872a4ded download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.04 KB e1549cfa download
processor_config.json 902 B 13e92a44 download

README current version from Hugging Face

license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
pipeline_tag: any-to-any
base_model: DavidAU/gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking
tags:

  • nightmedia
  • gemma4
  • gemma
  • google
  • bf16
  • mlx

gemma-4-E4B-it-The-DECKARD-V2-Strong-HERETIC-UNCENSORED-Thinking-bf16

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
bf16    0.509,0.721,0.780,0.656,0.432,0.773,0.639
mxfp8   0.515,0.712,0.785,0.656,0.426,0.767,0.639
 
Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8                    14.91 GB      1172

Baseline model

         arc   arc/e boolq hswag obkqa piqa  wino
bf16     0.490,0.674,0.793,0.612,0.416,0.756,0.669
mxfp8    0.480,0.656,0.797,0.608,0.400,0.755,0.665
mxfp4    0.455,0.607,0.851,0.585,0.402,0.744,0.651

Quant    Perplexity      Peak Memory   Tokens/sec
mxfp8    35.937 ± 0.525  14.80 GB      1153
mxfp4    36.746 ± 0.534  11.06 GB      1030

See parent model for instructions on install and use with Transformers.

-G

README history 13 versions

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

  1. 2026-04-15Update README.mdf79c8da1 KB
    Loading...
  2. 2026-04-15Update README.mda68eae71.1 KB
    Loading...
  3. 2026-04-14Update README.md068a96f1.1 KB
    Loading...
  4. 2026-04-13Update README.md4d0589a1 KB
    Loading...
  5. 2026-04-13Update README.mda8272941 KB
    Loading...
  6. 2026-04-13Update README.md27e560d1.8 KB
    Loading...
  7. 2026-04-13Update README.mda16c88c2 KB
    Loading...
  8. 2026-04-09Update README.mdd4b989f2 KB
    Loading...
  9. 2026-04-08Update README.md19a26121.9 KB
    Loading...
  10. 2026-04-08Update README.mde58f3da1.9 KB
    Loading...
  11. 2026-04-08Update README.md6330b311.9 KB
    Loading...
  12. 2026-04-08Update README.md4e218731.9 KB
    Loading...
  13. 2026-04-08Add files using upload-large-folder tool5240fb6575 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