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

Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot-GGUF

Rangle2 Gemma 12B GGUF 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/Rangle2%2Fgemma-4-12B-it-uncensored-opus4.7-cot-GGUF"
Response includes
  • classification m-uncensored
  • files 9
  • hub_downloads_all_time 2,616
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=Rangle2
All 2 models by Rangle2
 GET/models?family=gemma&method=m-uncensored
Sibling gemma models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
3K
636 last 30d - stable
Likes
0
Model age
3mo ago
created 2026-06-25
Downloads over time
Now2.7K→from284↑860%
1621.1K2K3K284 on Jun 242.7K on Oct 11JunJulAugSepOct
Jun 24 → Oct 11 · 55 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.

Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot↓ 1,282 this lineage
Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot-GGUF↓ 636

Variants by this author 2 formats · 2K downloads combined

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

Metadata

Quantizations
F16 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
gguf llama.cpp quantized gemma text-generation base_model:Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot base_model:quantized:Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot endpoints_compatible region:us conversational

Related

Other by Rangle2
gemma-4-12B-it-uncensored-opus4.7-cot 1K
Same base model
mradermacher/gemma-4-12B-it-uncensored-opus4.7-cot-i1-GGUF 3K mradermacher/gemma-4-12B-uncensored-opus4.7-cot-i1-GGUF 2K mradermacher/gemma-4-12B-uncensored-opus4.7-cot-GGUF 557 mradermacher/gemma-4-12B-it-uncensored-opus4.7-cot-GGUF 478
Total size
68.1 GB
Files
9
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2026-06-25 12:31
Source huggingface.co/Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot-GGUF ↗ Base model Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot →

Files by quantization

F16 1 file 22.2 GB
gemma-4-12B-it-uncensored-opus4.7-cot-F16.gguf 22.2 GB f42342cf download
Q8_0 1 file 11.8 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q8_0.gguf 11.8 GB 1f75e15f download
Q6_K 1 file 9.11 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q6_K.gguf 9.11 GB 3f29c917 download
Q5_K 1 file 7.96 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q5_K_M.gguf 7.96 GB 3e887feb download
Q4_K 1 file 6.87 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q4_K_M.gguf 6.87 GB 680d1992 download
Q3_K 1 file 5.67 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q3_K_M.gguf 5.67 GB 7a42f70a download
Q2_K 1 file 4.50 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q2_K.gguf 4.50 GB d87a9fe6 download
Auxiliary files 2 files 3.21 KB
.gitattributes 2.06 KB 251c06a0 download
README.md 1.15 KB f7e5c294 download

README current version from Hugging Face

base_model: Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot
base_model_relation: quantized
library_name: gguf
pipeline_tag: text-generation
tags:

  • gguf
  • llama.cpp
  • quantized
  • gemma

gemma-4-12B-it-uncensored-opus4.7-cot — GGUF

GGUF quantizations of Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot.

Produced with llama.cpp (llama-quantize) from an F16 GGUF converted directly from the base safetensors.

Available quants

File Quant Size
gemma-4-12B-it-uncensored-opus4.7-cot-Q2_K.gguf Q2_K 4.83 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q3_K_M.gguf Q3_K_M 6.09 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q4_K_M.gguf Q4_K_M 7.38 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q5_K_M.gguf Q5_K_M 8.55 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q6_K.gguf Q6_K 9.79 GB
gemma-4-12B-it-uncensored-opus4.7-cot-Q8_0.gguf Q8_0 12.67 GB
gemma-4-12B-it-uncensored-opus4.7-cot-F16.gguf F16 23.83 GB

Usage

llama-cli -hf Rangle2/gemma-4-12B-it-uncensored-opus4.7-cot-GGUF:Q4_K_M

README history 1 version

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

  1. 2026-06-25Upload README.md with huggingface_hub89428541.1 KB
    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