← back to catalog · registered 2026-11-12 01:03

mradermacher/gemma-4-26B-A4B-it-abliterated-v3-GGUF

mradermacher Gemma 26B GGUF MoE
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-4-26B-A4B-it-abliterated-v3-GGUF"
Response includes
  • classification m8
  • files 9
  • author_summary 3602 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • author=mradermacher (M8 quantization producer)
  • is_gguf=1
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
2K
Likes
0
Model age
1w ago
created 2026-11-12
Downloads over time
Now 1.7K → from 0 ↑ 0%
06311.3K1.9K 0 on Nov 12 1.7K on Nov 22 Nov
Nov 12 → Nov 22 · 11 snapshots · spans 10 days

Variants by this author 2 formats · 9K downloads combined

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

Metadata

Quantizations
Q2_K Q3_K Q4_K Q6_K Q8_0
Tags
transformers gguf abliteration refusal-direction cybersecurity interpretability research gemma en es base_model:jsantillana/gemma-4-26B-A4B-it-abliterated-v3 base_model:quantized:jsantillana/gemma-4-26B-A4B-it-abliterated-v3

Related

Total size
82.7 GB
Files
9
Quantizations
7
Registered
2026-11-12 01:03
Last updated on HF
2026-11-12 03:51

Files by quantization

Q8_0 2 files 25.8 GB
gemma-4-26B-A4B-it-abliterated-v3.Q8_0.gguf 25.0 GB 7a2259fe download
gemma-4-26B-A4B-it-abliterated-v3.mmproj-Q8_0.gguf 769 MB e801bfe1 download
Q6_K 1 file 21.1 GB
gemma-4-26B-A4B-it-abliterated-v3.Q6_K.gguf 21.1 GB ff5d75b5 download
Q4_K 1 file 14.4 GB
gemma-4-26B-A4B-it-abliterated-v3.Q4_K_S.gguf 14.4 GB 908bbc94 download
Q3_K 1 file 12.4 GB
gemma-4-26B-A4B-it-abliterated-v3.Q3_K_M.gguf 12.4 GB 4c74c3d8 download
Q2_K 1 file 9.86 GB
gemma-4-26B-A4B-it-abliterated-v3.Q2_K.gguf 9.86 GB d3ae47f8 download
F16 1 file 1.11 GB
gemma-4-26B-A4B-it-abliterated-v3.mmproj-f16.gguf 1.11 GB 0413f314 download
Auxiliary files 2 files 2.43 KB
.gitattributes 2.05 KB 31c1e37a download
README.md 388 B 0cf62732 download

README current version from Hugging Face

README history 4 versions

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

  1. 2026-11-12 auto-patch README.md ced7d6d 4.3 KB
    Loading...
  2. 2026-11-12 auto-patch README.md 340bbf6 4.4 KB
    Loading...
  3. 2026-11-12 auto-patch README.md 8e5760f 4.2 KB
    Loading...
  4. 2026-11-12 uploaded from rich1 b5c39e7 388 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