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

ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-vlm-4Bit

ailexleon Gemma 31B multimodal 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/ailexleon%2Fgemma-4-31B-it-qat-uncensored-heretic-mlx-vlm-4Bit"
Response includes
  • classification m3
  • files 13
  • hub_downloads_all_time 1,887
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=ailexleon
All 15 models by ailexleon
 GET/models?family=gemma&method=m3
Sibling gemma models · same method
 GET/methods/m3
What "m3" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M3
Primary method

Layer-wise ablation

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 2 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • 'heretic' in model name (Heretic-produced)
  • Heretic uses layer-wise optimization (M3) with underlying direction removal (M1)
How we label → About M3 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
2K
426 last 30d - stable
Likes
2
Model age
2mo ago
created 2026-07-18
Downloads over time
Now2.1K→from0↑0%
07591.5K2.3K0 on Jul 152.1K on Oct 11JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 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.

llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic↓ 76 this lineage
ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-vlm-4Bit↓ 426

Metadata

License
apache-2.0
Tags
mlx safetensors gemma4 heretic uncensored decensored abliterated ara image-text-to-text conversational en base_model:llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic

Related

Other by ailexleon
gemma-4-12B-it-qat-uncensored-heretic-mlx-4Bit 2K gemma-4-26B-A4B-it-qat-uncensored-heretic-mlx-vlm-4Bit 1K gemma-4-31B-it-qat-uncensored-heretic-mlx-lm-4Bit 818 Huihui-Qwen3.8-27B-abliterated-mlx-4Bit 726 Huihui-Qwen3.8-27B-abliterated-mlx-8Bit 638
Same base model
mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic-i1-GGUF 3K llmfan46/gemma-4-31B-it-qat-q4_0-uncensored-heretic-GGUF 2K ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-lm-4Bit 818 mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic-GGUF 638 llmfan46/gemma-4-31B-it-qat-q4_0-uncensored-heretic-NVFP4-GGUF 533
Total size
17.1 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-18 11:44
Source huggingface.co/ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-vlm-4Bit ↗ Base model llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic →

Files by quantization

Auxiliary files 13 files 17.2 GB
model-00003-of-00004.safetensors 5.00 GB ed21f79e download
model-00001-of-00004.safetensors 5.00 GB df16673d download
model-00002-of-00004.safetensors 4.99 GB 037e88b9 download
model-00004-of-00004.safetensors 2.16 GB 3933de40 download
tokenizer.json 30.7 MB a2619fe1 download
model.safetensors.index.json 201 KB 035c187f download
chat_template.jinja 18.2 KB 4741bf6e download
config.json 5.89 KB 897b8289 download
tokenizer_config.json 2.75 KB dc684e39 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.29 KB a086fb7e download
README.md 1.01 KB 058af171 download
generation_config.json 218 B 44dfdff4 download

README current version from Hugging Face

base_model: llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic
license: apache-2.0
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
language: en
tags:

  • mlx
  • heretic
  • uncensored
  • decensored
  • abliterated
  • ara
    library_name: mlx
    pipeline_tag: image-text-to-text

ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-vlm-4Bit

Converted to MLX format from llmfan46/gemma-4-31B-it-qat-q4_0-unquantized-uncensored-heretic using mlx-vlm version 0.6.3.

If you don't need vision capabilities, use ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-lm-4Bit.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model ailexleon/gemma-4-31B-it-qat-uncensored-heretic-mlx-vlm-4Bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

README history 2 versions

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

  1. 2026-07-18Update README.md18493e31 KB
    Loading...
  2. 2026-07-18Upload folder using huggingface_hub13e0782401 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