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

mykor/supergemma4-26b-abliterated-multimodal

mykor Gemma 26B MoE multimodal
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/mykor%2Fsupergemma4-26b-abliterated-multimodal"
Response includes
  • classification m1
  • files 11
  • benchmarks 11 entries
  • hub_downloads_all_time 174
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=gemma&method=m1
Sibling gemma models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 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.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
174
30 last 30d - stable
Likes
0
Descendants
2
in 2 direct forks
Model age
5mo ago
created 2026-04-17
Downloads over time
Now181→from54↑235%
489614519454 on Apr 15181 on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 2.2 UGI
Hazardous 2.9 UGI
Natural Intelligence 34.44 UGI
Political lean -18.2% UGI
Sensitive-Info 22.41 UGI
SocPol 1.8 UGI
UGI 20.77 UGI
Willingness (10) 1.8 UGI
W10-Adherence 1.5 UGI
W10-Direct 2 UGI
Writing 41.62 UGI

Genealogy 2 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.

google/gemma-4-26B-A4B-it this lineage
mykor/supergemma4-26b-abliterated-multimodal↓ 30 2 forks
mradermacher/supergemma4-26b-abliterated-multimodal-GGUF↓ 1,707
mradermacher/supergemma4-26b-abliterated-multimodal-i1-GGUF↓ 1,351

Metadata

License
gemma
Languages
en ko
Tags
transformers safetensors gemma4 image-text-to-text abliterated conversational en ko base_model:Jiunsong/supergemma4-26b-abliterated-multimodal base_model:finetune:Jiunsong/supergemma4-26b-abliterated-multimodal license:gemma endpoints_compatible

Related

Same base model
HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-HauhauCS-Balanced-MTP 411K HauhauCS/Gemma4-26B-A4B-Uncensored-HauhauCS-Balanced 72K Jiunsong/supergemma4-26b-uncensored-gguf-v2 48K Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2 9K OS-Software/gemma-4-26B-A4B-it-qat-q4_0-uncensored-heretic-v2-GGUF 3K
Total size
48.1 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-22 05:13
Source huggingface.co/mykor/supergemma4-26b-abliterated-multimodal ↗ Base model google/gemma-4-26B-A4B-it ↗

Files by quantization

Auxiliary files 11 files 48.1 GB
model-00001-of-00002.safetensors 27.7 GB eae9c10b download
model-00002-of-00002.safetensors 20.4 GB fdb69770 download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 101 KB c788b05b download
chat_template.jinja 31.8 KB dc7680e2 download
config.json 3.73 KB c6f5d5fa download
tokenizer_config.json 2.62 KB f07b8ede download
processor_config.json 1.65 KB 5465974d download
.gitattributes 1.53 KB 52373fe2 download
README.md 696 B 30d47f69 download
generation_config.json 179 B cfb6dd47 download

README current version from Hugging Face

license: gemma
language:

  • en
  • ko
    base_model:
  • google/gemma-4-26B-A4B-it
  • Jiunsong/supergemma4-26b-abliterated-multimodal
    tags:
  • abliterated
    pipeline_tag: image-text-to-text
    library_name: transformers

supergemma4-26b-abliterated-multimodal

transformers >= 5.5.0

transformers 라이브러리에서 오류없이 불러올 수 있도록 조정된 supergemma4-26b-abliterated-multimodal 모델

from transformers import AutoTokenizer, AutoProcessor, AutoModelForCausalLM

repo = "mykor/supergemma4-26b-abliterated-multimodal"
tokenizer = AutoTokenizer.from_pretrained(repo)
processor = AutoProcessor.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo)

README history 2 versions

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

  1. 2026-04-22Update README.mdbc52cec696 B
    Loading...
  2. 2026-04-17Create README.md719ecd1254 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