← back to catalog · registered 2026-09-27 21:57

otherwhere1/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-mlx-8Bit

otherwhere1 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/otherwhere1%2FQwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-mlx-8Bit"
Response includes
  • classification m3
  • files 15
  • hub_downloads_all_time 68
  • author_summary 2 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
68
Likes
0
Model age
7w ago
created 2026-09-27
Downloads over time
Now 627 → from 0 ↑ 0%
0230460690 0 on Sep 27 627 on Nov 22 SepOctNov
Sep 27 → Nov 22 · 57 snapshots · spans 56 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.

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3_5_moe image-text-to-text qwen3_5 heretic uncensored decensored abliterated mpoa mtp mlx

Related

Total size
34.3 GB
Files
15
Quantizations
1
Registered
2026-09-27 21:57
Last updated on HF
2026-09-27 21:30

Files by quantization

Auxiliary files 15 files 34.3 GB
model-00003-of-00007.safetensors 5.00 GB bccdfb7e download
model-00005-of-00007.safetensors 5.00 GB 76c937ea download
model-00004-of-00007.safetensors 4.99 GB e58e6a16 download
model-00006-of-00007.safetensors 4.99 GB ef7d0504 download
model-00002-of-00007.safetensors 4.99 GB 20426e06 download
model-00001-of-00007.safetensors 4.97 GB e86a0b28 download
model-00007-of-00007.safetensors 4.37 GB 30939c87 download
tokenizer.json 19.1 MB 06b95093 download
model.safetensors.index.json 183 KB 013fee30 download
config.json 22.6 KB d5665ddd download
chat_template.jinja 11.5 KB 03a040a2 download
.gitattributes 1.53 KB 52373fe2 download
README.md 1.34 KB 55d522fb download
tokenizer_config.json 1.24 KB 30d3b90a download
generation_config.json 226 B 2dd033e0 download

README current version from Hugging Face


library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE
pipeline_tag: image-text-to-text
tags:

  • qwen3_5
  • heretic
  • uncensored
  • decensored
  • abliterated
  • mpoa
  • mtp
  • mlx
  • mlx-my-repo
    base_model: llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved

otherwhere1/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-mlx-8Bit

The Model otherwhere1/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-mlx-8Bit was converted to MLX format from llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved using mlx-lm version 0.31.2.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("otherwhere1/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-mlx-8Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)

README history 1 version

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

  1. 2026-09-27 Upload folder using huggingface_hub 7576a47 1.3 KB
    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