← back to catalog · registered 2026-09-12 02:55

ktakemoto/gemma-4-31b-uncensored-heretic-testing-copy

ktakemoto Gemma 31B GGUF 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/ktakemoto%2Fgemma-4-31b-uncensored-heretic-testing-copy"
Response includes
  • classification m3
  • files 13
  • hub_downloads_all_time 799
  • author_summary 1 models
  • readme_text full
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
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · lifetime
799
141 last 30d - stable
Likes
0
Model age
6w ago
created 2026-09-12
Downloads over time
Now929→from0↑0%
03416811K0 on Sep 12929 on Oct 27SepOct
Sep 12 → Oct 27 · 46 snapshots · spans 45 days

Metadata

Quantizations
BF16 Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf endpoints_compatible region:us conversational
Total size
215 GB
Files
13
Quantizations
7
Registered
2026-09-12 02:55
Last updated on HF
2026-09-12 02:16

Files by quantization

BF16 2 files 58.3 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-BF16.gguf 57.2 GB e081939a download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-mmproj-BF16.gguf 1.12 GB c040f829 download
Q8_0 1 file 30.4 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q8_0.gguf 30.4 GB 688170f6 download
Q6_K 1 file 23.5 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q6_K.gguf 23.5 GB fb82b4d4 download
Q5_K 2 files 40.2 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q5_K_M.gguf 20.3 GB 0b2bd578 download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q5_K_S.gguf 19.8 GB 9cd18f58 download
Q4_K 2 files 33.9 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q4_K_M.gguf 17.4 GB aefb0b5a download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q4_K_S.gguf 16.5 GB dd38f9d1 download
Q3_K 2 files 29.7 GB
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q3_K_L.gguf 15.5 GB 44f48987 download
gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncensored-heretic-Q3_K_M.gguf 14.2 GB 83faab45 download
Auxiliary files 3 files 154 MB
ortenzya.webp 154 MB b6dd3cfe download
.gitattributes 2.64 KB fd57cbaf download
README.md 0 B e69de29b download

README

README history 2 versions

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

  1. 2026-09-12Update README.md95ecbf00 B
    Loading...
  2. 2026-09-12Duplicate from llmfan46/gemma-4-Ortenzya-The-Creative-Wordsmith-31B-it-uncens...fab929832.7 KB
    Loading...

Discussions 1 thread

  1. 2026-09-17PRCreate README.mdopen1 💬#1
    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.

Open in Abliteration