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

Justanut/Ornith-1.0-35B-uncensored-heretic-oQ6e

Justanut 35B MoE
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/Justanut%2FOrnith-1.0-35B-uncensored-heretic-oQ6e"
Response includes
  • classification m3
  • files 17
  • hub_downloads_all_time 1,343
  • author_summary 3 models
  • readme_text full
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
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
HIGH
Why we say so
name contains 'heretic'; Heretic default extraction is difference-of-means (Arditi 2024)
Downloads · lifetime
1K
47 last 30d - cooling
Likes
0
Model age
3mo ago
created 2026-07-13
Downloads over time
Now1.4K→from754↑80%
7249561.2K1.4K754 on Jul 151.4K on Oct 11JulAugSepOct
Jul 15 → Oct 11 · 53 snapshots · spans 88 days

Metadata

Tags
mlx safetensors qwen3_5_moe oq quantized 6-bit region:us

Related

Total size
27.4 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-13 12:57

Files by quantization

Auxiliary files 17 files 27.4 GB
model-00001-of-00006.safetensors 4.86 GB 8c3ed97f download
model-00004-of-00006.safetensors 4.67 GB 92e0d496 download
model-00003-of-00006.safetensors 4.67 GB 49f91a79 download
model-00005-of-00006.safetensors 4.67 GB 1ad2980c download
model-00002-of-00006.safetensors 4.67 GB a3f20212 download
model-00006-of-00006.safetensors 3.86 GB 40936a9b download
tokenizer.json 19.1 MB 6f32ce20 download
model.safetensors.index.json 196 KB c9983f93 download
config.json 65.9 KB eb2ca3f4 download
oq_imatrix_report.json 30.8 KB a04432cc download
chat_template.jinja 7.83 KB 1e6f3b77 download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.17 KB 7b0f9106 download
processor_config.json 1.16 KB 33818c7f download
preprocessor_config.json 390 B 2ea84a43 download
README.md 331 B 08653331 download
generation_config.json 227 B e8f101cd download

README current version from Hugging Face


library_name: mlx
tags:

  • mlx
  • oq
  • quantized

Ornith-1.0-35B-uncensored-heretic-oQ6e

This model was quantized using oQ (oMLX v0.5.1) mixed-precision quantization.

Quantization details

  • Model type: qwen3_5_moe
  • Bits: 6
  • Group size: 64
  • Format: MLX safetensors

README history 1 version

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

  1. 2026-07-13Upload Ornith-1.0-35B-uncensored-heretic-oQ6e via oMLXd9de19d331 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