← back to catalog · registered 2026-11-12 20:03

cyburn/gemma-4-12B-abliterated-mlx-4bit

cyburn Gemma 12B
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/cyburn%2Fgemma-4-12B-abliterated-mlx-4bit"
Response includes
  • classification m1
  • files 12
  • author_summary 1 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
125
Likes
0
Model age
1w ago
created 2026-11-12
Downloads over time
Now 125 → from 0 ↑ 0%
04692138 0 on Nov 12 125 on Nov 22 Nov
Nov 12 → Nov 22 · 11 snapshots · spans 10 days

Metadata

Tags
mlx safetensors gemma4_unified text-generation conversational en 4-bit region:us
Total size
6.33 GB
Files
12
Quantizations
1
Registered
2026-11-12 20:03
Last updated on HF
2026-11-12 20:10

Files by quantization

Auxiliary files 12 files 6.36 GB
model-00001-of-00002.safetensors 4.98 GB 72e39ec9 download
model-00002-of-00002.safetensors 1.25 GB e2db4160 download
model-vision.safetensors 95.2 MB 025a2c8f download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 132 KB 523b1e02 download
chat_template.jinja 17.1 KB e61bbfe9 download
config.json 3.86 KB 59ca1338 download
tokenizer_config.json 2.71 KB 1cb36051 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.35 KB b889adcd download
generation_config.json 260 B d09dccf1 download
README.md 81.0 B 1046b24f download

README current version from Hugging Face


language: en
library_name: mlx
pipeline_tag: text-generation
tags:

  • mlx

README history 1 version

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

  1. 2026-11-12 Upload folder using huggingface_hub e3cc038 81 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