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

yabaimimi/edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-GGUF

yabaimimi 26B GGUF MoE second-order 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/yabaimimi%2Fedwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-GGUF"
Response includes
  • classification m3
  • files 16
  • hub_downloads_all_time 27,960
  • author_summary 1 models
  • readme_text full
Try next
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
28K
3K last 30d - stable
Likes
5
Model age
3mo ago
created 2026-06-20
Downloads over time
Now28.4K→from2.3K↑1,148%
97011K21K31K2.3K on Jun 2428.4K on Oct 11JunJulAugSepOct
Jun 24 → Oct 11 · 56 snapshots · spans 109 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.

edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored↓ 294 this lineage
yabaimimi/edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-GGUF↓ 3,125

Metadata

License
apache-2.0
Quantizations
BF16 F16 IQ3 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf base_model:edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored base_model:quantized:edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored license:apache-2.0 endpoints_compatible region:us conversational
Total size
262 GB
Files
16
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2026-06-21 09:28
Source huggingface.co/yabaimimi/edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-GGUF ↗ Base model edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored →

Files by quantization

BF16 1 file 47.1 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-BF16.gguf 47.1 GB dca8065a download
F16 1 file 47.1 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-FP16.gguf 47.1 GB 0f168e9b download
Q8_0 1 file 25.0 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q8_0.gguf 25.0 GB 21e5d935 download
Q6_K 1 file 21.1 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q6_K.gguf 21.1 GB d495305c download
Q5_K 1 file 17.8 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q5_K_M.gguf 17.8 GB 8c1a7a47 download
Q4_K 1 file 15.7 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q4_K_M.gguf 15.7 GB 43aa497e download
IQ4 2 files 26.7 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ4_NL.gguf 13.6 GB acff7d7c download
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ4_XS.gguf 13.1 GB 1c7ead0a download
Q3_K 1 file 12.4 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q3_K_M.gguf 12.4 GB f3e4d30e download
IQ3 2 files 22.9 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ3_M.gguf 11.5 GB a1350353 download
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-IQ3_S.gguf 11.4 GB 7a951f1e download
Q2_K 1 file 9.86 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-Q2_K.gguf 9.86 GB 87a946a5 download
Auxiliary files 4 files 16.7 GB
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-TQ2_0.gguf 8.72 GB a28bb408 download
edwixx__diffusiongemma-26B-A4B-it-HERETIC-Uncensored-TQ1_0.gguf 7.99 GB 6e5d9af4 download
.gitattributes 2.85 KB 8e73ca5e download
README.md 865 B 1599a377 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored

Model Card

Description

This model is the unmodified, GGUF quantized version of edwixx/diffusiongemma-26B-A4B-it-HERETIC-Uncensored.

Terms of Use

By downloading or running this model, you accept all the terms listed below:

  • You accept full responsibility for any harmful use or output generated by this model.
  • You confirm that you are a legal adult in your jurisdiction and at least 18 years old.
  • The author takes no responsibility for any misuse, harmful content, or actions produced by or with this model.
  • This model is provided "as-is" with no warranty of any kind.

⚠️ By downloading or running this model you accept all terms above.

README history 3 versions

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

  1. 2026-06-21Update README.md3542e8e865 B
    Loading...
  2. 2026-06-21Update README.mdf428264659 B
    Loading...
  3. 2026-06-21Create README.md755701893 B
    Loading...

Discussions 1 thread

  1. 2026-07-25Mmproj?closed2 💬#1
    Loading...

Continue on Hugging Face →

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