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

hehua2008/gemma-4-26B-A4B-it-abliterated-MLX

hehua2008 Gemma 26B MoE 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/hehua2008%2Fgemma-4-26B-A4B-it-abliterated-MLX"
Response includes
  • classification m1
  • files 20
  • hub_downloads_all_time 384
  • author_summary 14 models
  • readme_text full
Try next
GET/models?author=hehua2008
All 14 models by hehua2008
 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
384
44 last 30d - stable
Likes
0
Model age
4mo ago
created 2026-06-08
Downloads over time
Now398→from84↑374%
6818930942984 on Jun 10398 on Oct 11398 on Oct 9JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 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-4-26B-A4B-it-abliterated↓ 1,228 this lineage
hehua2008/gemma-4-26B-A4B-it-abliterated-MLX↓ 44

Metadata

License
apache-2.0
Tags
mlx safetensors gemma4 abliterated uncensored any-to-any base_model:huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated base_model:finetune:huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated license:apache-2.0 region:us

Related

Other by hehua2008
Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-4bit 325 Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-mixed_3_4 221 Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit 214 gemma-4-26B-A4B-it-abliterated-MLX-4bit 151 Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-6bit 136
Same base model
groxaxo/Huihui-gemma-4-26B-A4B-it-abliterated-GGUF 31K mradermacher/Huihui-gemma-4-26B-A4B-it-abliterated-i1-GGUF 2K mradermacher/Huihui-gemma-4-26B-A4B-it-abliterated-GGUF 2K deewu0809/gemma-4-26B-A4B-it-abliterated-GGUF 737 leonsarmiento/Huihui-gemma-4-26B-A4B-it-abliterated-3bit-XL-mlx 619
Total size
48.1 GB
Files
20
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-08-15 02:37
Source huggingface.co/hehua2008/gemma-4-26B-A4B-it-abliterated-MLX ↗ Base model huihui-ai/Huihui-gemma-4-26B-A4B-it-abliterated →

Files by quantization

Auxiliary files 20 files 48.1 GB
model-00001-of-00011.safetensors 4.98 GB 3d3abd75 download
model-00008-of-00011.safetensors 4.58 GB b2585a28 download
model-00010-of-00011.safetensors 4.58 GB 85066434 download
model-00004-of-00011.safetensors 4.58 GB 9a84e505 download
model-00002-of-00011.safetensors 4.58 GB 43b4c896 download
model-00006-of-00011.safetensors 4.58 GB d67c2b09 download
model-00009-of-00011.safetensors 4.55 GB 44e070a8 download
model-00007-of-00011.safetensors 4.55 GB 14b6c407 download
model-00005-of-00011.safetensors 4.55 GB 7ef792d3 download
model-00003-of-00011.safetensors 4.55 GB 54bd55d1 download
model-00011-of-00011.safetensors 2.01 GB 9e1e4bcb download
tokenizer.json 30.7 MB cc8d3a0c download
model.safetensors.index.json 107 KB 06e5d873 download
chat_template.jinja 11.8 KB 33c51c2d download
config.json 4.74 KB 6546e37c 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 859 B 77491915 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-4-26B-A4B-it-abliterated
tags:

  • abliterated
  • uncensored
  • mlx

hehua2008/gemma-4-26B-A4B-it-abliterated-MLX

This model was converted to MLX format from huihui-ai/Huihui-gemma-4-26B-A4B-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 hehua2008/gemma-4-26B-A4B-it-abliterated-MLX --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 3 versions

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

  1. 2026-08-15Upload folder using huggingface_hub0dfd5bf859 B
    Loading...
  2. 2026-06-08Upload folder using huggingface_hub0a52c06858 B
    Loading...
  3. 2026-06-08initial commit4950bc828 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