Get the app
← back to catalog · registered 2026-09-13 16:56

SOMEHOTMEAL/Gemma-3-12B-Janus-Abliterated-V2-Base_And_GGUF

SOMEHOTMEAL Gemma 12B GGUF multimodal second-order 131K 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/SOMEHOTMEAL%2FGemma-3-12B-Janus-Abliterated-V2-Base_And_GGUF"
Response includes
  • classification m5
  • files 20
  • hub_downloads_all_time 579
  • author_summary 13 models
  • readme_text full
Try next
GET/models?author=SOMEHOTMEAL
All 13 models by SOMEHOTMEAL
 GET/models?family=gemma&method=m5
Sibling gemma models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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 · lifetime
579
446 last 30d - active
Likes
2
Model age
6w ago
created 2026-09-13
Downloads over time
Now988→from0↑0%
03627251.1K0 on Sep 13988 on Oct 28SepOct
Sep 13 → Oct 28 · 46 snapshots · spans 45 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.

DreamFast/gemma-3-12b-it-heretic this lineage
SOMEHOTMEAL/Gemma-3-12B-Janus-Abliterated-V2-Base_And_GGUF↓ 446

Metadata

Quantizations
Q4_K
Tags
transformers safetensors gguf gemma3 image-text-to-text mergekit merge conversational arxiv:2311.03099 base_model:DreamFast/gemma-3-12b-it-heretic base_model:merge:DreamFast/gemma-3-12b-it-heretic base_model:google/gemma-3-12b-it

Related

Other by SOMEHOTMEAL
LLama-3.1-8B-Janus-Abliterated-V2-Base_And_GGUF 564 Ministral-3-14B-Janus-Abliterated-V2-Base_And_GGUF 544 _Broken-quants_Gemma-4-12B-Janus-Abliterated-V2-Base_And_GGUF 375 Qwen3.5-9B-Janus-Abliterated-V2-Base_And_GGUF 325 Qwen3.5-9B-Janus-Abliterated-V2-Safetensors 210
Same base model
nightmedia/gemma-3-12b-it-vl-GLM-4.7-Flash-Polaris-Heretic-Uncensored-Thinking-qx86-hi-mlx 179 nightmedia/gemma-3-12b-it-vl-Kimi-K2-Heretic-Uncensored-Thinking-qx86-hi-mlx 172 nightmedia/gemma-3-12b-it-vl-GLM-4.7-Flash-Heretic-Uncensored-Thinking-qx86-hi-mlx 102 DavidAU/gemma-3-12b-it-vl-Gemini-3-Pro-Preview-Heretic-Uncensored-Thinking 92 DavidAU/gemma-3-12b-it-vl-GLM-4.7-Flash-Heretic-Uncensored-Thinking 87
Total size
76.5 GB
Files
20
Quantizations
2
Registered
2026-09-13 16:56
Last updated on HF
2026-09-13 16:25
Source huggingface.co/SOMEHOTMEAL/Gemma-3-12B-Janus-Abliterated-V2-Base_And_GGUF ↗ Base model DreamFast/gemma-3-12b-it-heretic ↗

Files by quantization

Q4_K 1 file 6.81 GB
Gemma-3-12B-Janus-Abliterated-V2-Q4_K_M-GGUF.gguf 6.81 GB e5377bd9 download
Auxiliary files 19 files 69.8 GB
Gemma-3-12B-Janus-Abliterated-V2-f16-GGUF.gguf 21.9 GB 25cca4e6 download
Gemma-3-12B-Janus-Abliterated-V2-Q8_0-GGUF.gguf 11.7 GB 53e0165a download
Gemma-3-12B-Janus-Abliterated-V2-Q6_K-GGUF.gguf 9.00 GB 7b8f9f71 download
model-00001-of-00005.safetensors 4.60 GB 91935785 download
model-00002-of-00005.safetensors 4.59 GB f7005db1 download
model-00003-of-00005.safetensors 4.59 GB 79ee6f10 download
model-00004-of-00005.safetensors 4.59 GB 92af52df download
Gemma-3-12B-Janus-Abliterated-V2-Q2_K-GGUF.gguf 4.45 GB 23d03e33 download
model-00005-of-00005.safetensors 4.32 GB 5ea772ea download
tokenizer.json 31.8 MB daab2354 download
model.safetensors.index.json 107 KB a4e78050 download
config.json 3.14 KB f48a83bf download
.gitattributes 1.94 KB b1576985 download
chat_template.jinja 1.54 KB c5f13654 download
README.md 1002 B 92ee0a7a download
tokenizer_config.json 770 B f595772b download
preprocessor_config.json 570 B b1e00fc1 download
mergekit_config.yml 217 B c7a47977 download
processor_config.json 70.0 B 453c7966 download

README current version from Hugging Face

base_model:

  • DreamFast/gemma-3-12b-it-heretic
  • google/gemma-3-12b-it
    library_name: transformers
    tags:
  • mergekit
  • merge

Gemma-3-12B-Janus-Abliterated-V2

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear DARE merge method using google/gemma-3-12b-it as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: dare_linear
base_model: google/gemma-3-12b-it

models:
  - model: DreamFast/gemma-3-12b-it-heretic
    parameters:
      weight: 0.60
      density: 0.70

dtype: bfloat16
tokenizer_source: base

README history 1 version

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

  1. 2026-09-13Upload folder using huggingface_hub9bbd56b961 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