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

nightmedia/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx

nightmedia Gemma 31B multimodal 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-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx"
Response includes
  • classification m3
  • files 14
  • benchmarks 11 entries
  • hub_downloads_all_time 7,984
  • 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
8K
249 last 30d - cooling
Likes
2
Model age
6mo ago
created 2026-04-06
Downloads over time
Now8.1K→from3.6K↑127%
3.3K5.1K6.8K8.5K3.6K on Apr 158.1K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 days

Benchmarks

Benchmark Score Source
Entertainment 2.8 UGI
Hazardous 4.7 UGI
Natural Intelligence 34.42 UGI
Political lean -22.2% UGI
Sensitive-Info 32.29 UGI
SocPol 2.6 UGI
UGI 52.36 UGI
Willingness (10) 9.2 UGI
W10-Adherence 8.5 UGI
W10-Direct 10 UGI
Writing 38.68 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.

DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking↓ 540 this lineage
nightmedia/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx↓ 249

Metadata

License
apache-2.0
Tags
mlx safetensors gemma4 nightmedia gemma google Deckard(qx) image-text-to-text conversational base_model:DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking base_model:quantized:DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking license:apache-2.0

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-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-i1-GGUF 46K AEON-7/Gemma-4-31B-it-DECKARD-HERETIC-Uncensored-NVFP4 7K AEON-7/Gemma-4-31B-it-DECKARD-HERETIC-Uncensored-NVFP4-SVDQuant 7K mradermacher/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-GGUF 4K connstruct/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking 545
Total size
28.1 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-13 21:08
Source huggingface.co/nightmedia/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx ↗ Base model DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking →

Files by quantization

Auxiliary files 14 files 28.1 GB
model-00002-of-00006.safetensors 5.00 GB 181e20df download
model-00001-of-00006.safetensors 5.00 GB 85254c61 download
model-00005-of-00006.safetensors 4.98 GB 5e5ccf25 download
model-00003-of-00006.safetensors 4.95 GB 4fc6b1bd download
model-00004-of-00006.safetensors 4.95 GB 0ec0bb7e download
model-00006-of-00006.safetensors 3.18 GB 882c55e2 download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 201 KB caea1e9f download
config.json 104 KB 1af90617 download
chat_template.jinja 16.0 KB db5b86c9 download
tokenizer_config.json 2.63 KB 872a4ded download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 902 B 13e92a44 download
README.md 888 B 2cad721f download

README current version from Hugging Face

license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
pipeline_tag: image-text-to-text
base_model: DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
tags:

  • nightmedia
  • gemma4
  • gemma
  • google
  • Deckard(qx)
  • mlx

gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking-qx86-hi-mlx

This is a Deckard(qx) experimental quant.

Brainwaves

         arc   arc/e boolq hswag obkqa piqa  wino
qx86-hi  0.431,0.505,0.426,0.670,0.376,0.766,0.710
Instruct
qx86-hi  0.573,0.719,0.900,0.715,0.420,0.781,0.695

Base model

gemma-4-31B-it (Instruct)
qx86-hi  0.496,0.653,0.901,0.624,0.380,0.732,0.653

Previous model

gemma-3-27b-it-heretic
q8       0.557,0.711,0.868,0.533,0.452,0.706,0.695

As I don't have an easy way to test this until LMStudio supports it, please Like it only if you had a good experience.

Thank you,

-G

README history 8 versions

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

  1. 2026-04-08Update README.md24ad41a888 B
    Loading...
  2. 2026-04-07Update README.md8ec9a33828 B
    Loading...
  3. 2026-04-07Update README.mdffce111817 B
    Loading...
  4. 2026-04-06Update README.mde98eca2790 B
    Loading...
  5. 2026-04-06Update README.md86745e6705 B
    Loading...
  6. 2026-04-06Update README.md5960671620 B
    Loading...
  7. 2026-04-06Update README.mde2675be822 B
    Loading...
  8. 2026-04-06Add files using upload-large-folder tool54c2f3d569 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