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

ailexleon/Ornith-1.0-35B-uncensored-heretic-mlx-8Bit

ailexleon 35B MoE 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%2FOrnith-1.0-35B-uncensored-heretic-mlx-8Bit"
Response includes
  • classification m3
  • files 19
  • hub_downloads_all_time 2,022
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=ailexleon
All 15 models by ailexleon
 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
93 last 30d - cooling
Likes
0
Model age
3mo ago
created 2026-07-11
Downloads over time
Now2K→from650↑214%
5811.1K1.6K2.2K650 on Jul 152K 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/Ornith-1.0-35B-uncensored-heretic↓ 270 this lineage
ailexleon/Ornith-1.0-35B-uncensored-heretic-mlx-8Bit↓ 93

Metadata

License
mit
Tags
mlx safetensors qwen3_5_moe heretic uncensored decensored abliterated image-text-to-text conversational en base_model:llmfan46/Ornith-1.0-35B-uncensored-heretic base_model:quantized:llmfan46/Ornith-1.0-35B-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/Ornith-1.0-35B-uncensored-heretic-i1-GGUF 3K llmfan46/Ornith-1.0-35B-uncensored-heretic-GGUF 3K mradermacher/Ornith-1.0-35B-uncensored-heretic-GGUF 2K leonsarmiento/Ornith-1.0-35B-uncensored-heretic-5bit-XL-mlx 212 noctrex/Ornith-1.0-35B-uncensored-heretic-MXFP4_MOE-GGUF 167
Total size
35.1 GB
Files
19
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-29 17:49
Source huggingface.co/ailexleon/Ornith-1.0-35B-uncensored-heretic-mlx-8Bit ↗ Base model llmfan46/Ornith-1.0-35B-uncensored-heretic →

Files by quantization

Auxiliary files 19 files 35.1 GB
model-00004-of-00008.safetensors 5.00 GB 044550fa download
model-00006-of-00008.safetensors 5.00 GB 4036bf8e download
model-00002-of-00008.safetensors 5.00 GB ceb4989c download
model-00003-of-00008.safetensors 4.99 GB 40fcd489 download
model-00005-of-00008.safetensors 4.99 GB 15f87cf4 download
model-00001-of-00008.safetensors 4.96 GB 4f8d37e1 download
model-00007-of-00008.safetensors 4.69 GB 7ab49b95 download
model-00008-of-00008.safetensors 515 MB 259f82ef download
tokenizer.json 19.1 MB 6f32ce20 download
model.safetensors.index.json 211 KB 849923d1 download
config.json 23.6 KB 381717d4 download
chat_template.jinja 7.36 KB b07660cc download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.24 KB a9eacca6 download
processor_config.json 991 B 8f29fe38 download
README.md 680 B 8941becd download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
generation_config.json 227 B e8f101cd download

README current version from Hugging Face

language: en
pipeline_tag: image-text-to-text
tags:

  • mlx
  • heretic
  • uncensored
  • decensored
  • abliterated
    library_name: mlx
    license: mit
    base_model:
  • llmfan46/Ornith-1.0-35B-uncensored-heretic

ailexleon/Ornith-1.0-35B-uncensored-heretic-mlx-8Bit

Converted to MLX format from llmfan46/Ornith-1.0-35B-uncensored-heretic using mlx-vlm version 0.6.4.

Use with mlx

pip install -U mlx-vlm

python -m mlx_vlm.generate --model ailexleon/Ornith-1.0-35B-uncensored-heretic-mlx-8Bit --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. 2026-07-11Update README.md42fcd6b680 B
    Loading...
  2. 2026-07-11Upload folder using huggingface_hub5b57fbe385 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