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

EZCon/Huihui-gemma-4-E4B-it-abliterated-4bit-mlx

EZCon Gemma 7.5B second-order
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/EZCon%2FHuihui-gemma-4-E4B-it-abliterated-4bit-mlx"
Response includes
  • classification m1
  • files 12
  • hub_downloads_all_time 2,696
  • author_summary 31 models
  • readme_text full
Try next
GET/models?author=EZCon
All 31 models by EZCon
 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
3K
422 last 30d - stable
Likes
2
Model age
6mo ago
created 2026-04-11
Downloads over time
Now2.9K→from285↑908%
1561.1K2.1K3.1K285 on Apr 152.9K on Oct 11AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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.

huihui-ai/Huihui-gemma-4-E4B-it-abliterated↓ 2,041 this lineage
EZCon/Huihui-gemma-4-E4B-it-abliterated-4bit-mlx↓ 422

Metadata

License
apache-2.0
Tags
mlx safetensors gemma4 abliterated uncensored any-to-any base_model:huihui-ai/Huihui-gemma-4-E4B-it-abliterated base_model:quantized:huihui-ai/Huihui-gemma-4-E4B-it-abliterated license:apache-2.0 4-bit region:us

Related

Other by EZCon
Huihui-Qwen3-VL-4B-Instruct-abliterated-mlx 500 Qwen2-VL-2B-Instruct-abliterated-mlx 389 Huihui-Qwen3-VL-4B-Instruct-abliterated-8bit-mlx 379 Huihui-Qwen3-VL-2B-Instruct-abliterated-mlx 336 Huihui-Qwen3-VL-4B-Instruct-abliterated-4bit-mlx 298
Same base model
mradermacher/Huihui-gemma-4-E4B-it-abliterated-GGUF 5K mradermacher/Huihui-gemma-4-E4B-it-abliterated-i1-GGUF 1K vokash3/Huihui-gemma-4-E4B-it-abliterated-LiteRT-LM 267 lagive/Huihui-gemma-4-E4B-it-abliterated-GGUF 172 EZCon/Huihui-gemma-4-E4B-it-abliterated-4bit-g32-mxfp4-mixed_4_8-mlx 136
Total size
11.2 GB
Files
12
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-12 12:00
Source huggingface.co/EZCon/Huihui-gemma-4-E4B-it-abliterated-4bit-mlx ↗ Base model huihui-ai/Huihui-gemma-4-E4B-it-abliterated →

Files by quantization

Auxiliary files 12 files 11.2 GB
model.safetensors 4.79 GB 2d6a2048 download
model-00001-of-00002.safetensors 3.99 GB 0b86f367 download
model-00002-of-00002.safetensors 2.37 GB 5ae9ab6d download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 235 KB c03ce5f7 download
chat_template.jinja 11.6 KB afb1d517 download
config.json 6.47 KB 4ee08502 download
tokenizer_config.json 2.65 KB 9c79a145 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.31 KB bb6dee0c download
README.md 851 B b95d20c3 download
generation_config.json 208 B e605bb45 download

README current version from Hugging Face

library_name: mlx
license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
pipeline_tag: any-to-any
base_model: huihui-ai/Huihui-gemma-4-E4B-it-abliterated
tags:

  • abliterated
  • uncensored
  • mlx

EZCon/Huihui-gemma-4-E4B-it-abliterated-4bit-mlx

This model was converted to MLX format from huihui-ai/Huihui-gemma-4-E4B-it-abliterated
using mlx-vlm version 0.6.12.
Refer to the original model card for more details on the model.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model EZCon/Huihui-gemma-4-E4B-it-abliterated-4bit-mlx --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 5 versions

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

  1. 2026-08-12Upload folder using huggingface_hub692613d851 B
    Loading...
  2. 2026-07-15Upload folder using huggingface_hubbeb4307850 B
    Loading...
  3. 2026-07-08Upload folder using huggingface_huba5f40c2850 B
    Loading...
  4. 2026-05-19Upload folder using huggingface_hub21f2994850 B
    Loading...
  5. 2026-04-11Upload folder using huggingface_hub8ac6479850 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