← back to catalog · registered 2026-11-14 19:03

mradermacher/gemma-4-E4B-it-weight-space-programming-UNCENSORED-heretic-GGUF

mradermacher Gemma GGUF
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/mradermacher%2Fgemma-4-E4B-it-weight-space-programming-UNCENSORED-heretic-GGUF"
Response includes
  • classification m3
  • files 5
  • author_summary 3602 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 · 30-day
3K
Likes
1
Model age
1w ago
created 2026-11-14
Downloads over time
Now 2.7K → from 0 ↑ 0%
01K2K3K 0 on Nov 14 2.7K on Nov 22 Nov
Nov 14 → Nov 22 · 9 snapshots · spans 8 days

Variants by this author 2 formats · 14K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
F16
Tags
transformers gguf gemma4 weight-space-programming mechanistic-interpretability tool-calling agentic zero-training heretic uncensored decensored abliterated

Related

Total size
13.9 GB
Files
5
Quantizations
3
Registered
2026-11-14 19:03
Last updated on HF
2026-11-14 22:13

Files by quantization

F16 2 files 14.8 GB
gemma-4-E4B-it-weight-space-programming-UNCENSORED-heretic.f16.gguf 13.9 GB 7f008568 download
gemma-4-E4B-it-weight-space-programming-UNCENSORED-heretic.mmproj-f16.gguf 944 MB 4012a1b7 download
Q8_0 1 file 534 MB
gemma-4-E4B-it-weight-space-programming-UNCENSORED-heretic.mmproj-Q8_0.gguf 534 MB 59e22365 download
Auxiliary files 2 files 2.20 KB
.gitattributes 1.80 KB fdc18337 download
README.md 411 B dcccc801 download

README current version from Hugging Face

README history 3 versions

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

  1. 2026-11-14 auto-patch README.md 4694d50 5.2 KB
    Loading...
  2. 2026-11-14 auto-patch README.md c062e11 5.3 KB
    Loading...
  3. 2026-11-14 uploaded from leia ab37ed6 411 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.

Open in Abliteration