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

dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-oQ8

dawncr0w Qwen 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/dawncr0w%2FQwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-oQ8"
Response includes
  • classification m-uncensored
  • files 17
  • hub_downloads_all_time 7,171
  • author_summary 16 models
  • readme_text full
Try next
GET/models?author=dawncr0w
All 16 models by dawncr0w
 GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
7K
307 last 30d - cooling
Likes
4
Model age
4mo ago
created 2026-05-28
Downloads over time
Now7.3K→from2.5K↑187%
2.3K4.1K5.9K7.8K2.5K on Jun 107.3K on Oct 11JunJulAugSepOct
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.

ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16↓ 3,002 this lineage
dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-oQ8↓ 307

Metadata

License
apache-2.0
Tags
mlx safetensors qwen3_5_moe omlx qwen3.6 qwen3.5-moe image-text-to-text oq8 conversational base_model:ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16 base_model:quantized:ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16 license:apache-2.0

Related

Other by dawncr0w
Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-6bpw-MLX 1K Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-text-oQ4 499 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-4bit-MLX 476 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-5bpw-MLX 315 Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-oQ6 225
Same base model
dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-6bpw-MLX 1K cyberCyber99/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-4bit-MLX 519 dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-text-oQ4 499 dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-4bit-MLX 476 dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-OptiQ-5bpw-MLX 315
Total size
35.1 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-28 08:45
Source huggingface.co/dawncr0w/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-oQ8 ↗ Base model ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16 →

Files by quantization

Auxiliary files 17 files 35.1 GB
model-00001-of-00008.safetensors 4.83 GB bd05dc3d download
model-00004-of-00008.safetensors 4.78 GB 74a1b8b8 download
model-00005-of-00008.safetensors 4.78 GB 11a1742c download
model-00007-of-00008.safetensors 4.78 GB ff830ac7 download
model-00006-of-00008.safetensors 4.78 GB 8d412647 download
model-00003-of-00008.safetensors 4.78 GB e9386821 download
model-00002-of-00008.safetensors 4.78 GB ebbacc93 download
model-00008-of-00008.safetensors 1.59 GB 43b8cf63 download
tokenizer.json 19.1 MB adfe67f1 download
model.safetensors.index.json 195 KB 0e733d03 download
config.json 70.0 KB c2ad6b47 download
tokenizer_config.json 14.8 KB ab21e994 download
README.md 947 B 612e1cf0 download
special_tokens_map.json 437 B 1838f3b7 download
preprocessor_config.json 336 B 4ae180b4 download
generation_config.json 243 B be05abc6 download
.gitattributes 101 B 0fd17d2f download

README current version from Hugging Face

license: apache-2.0
base_model: ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16
library_name: mlx
tags:

  • mlx
  • omlx
  • qwen3.6
  • qwen3.5-moe
  • image-text-to-text
  • oq8

Qwen3.6-35B-A3B Uncensored HauhauCS Aggressive oQ8

This is an oMLX oQ8 VLM quantization of
ericpandev/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive-bf16.

Quantization

  • Quantizer: oMLX oQ
  • Level: oQ8
  • Group size: 64
  • Non-quantized/scales dtype: bfloat16
  • Output size: about 35 GB
  • Vision weights: preserved
  • Native MTP: disabled

Notes

The source checkpoint is a VLM-style BF16 conversion. This repository preserves
vision_config and model.visual.* tensors. Native MTP was disabled because
the BF16 source did not include mtp.* tensors.

Local validation confirmed the vision tensors are present, but the bundled
MLX-VLM runtime in oMLX did not support the qwen3_5_moe_vision model type at
the time of conversion.

README history 3 versions

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

  1. 2026-05-28Match oQ4 model card format9eb9558947 B
    Loading...
  2. 2026-05-28Update model cardf45cdcf1.9 KB
    Loading...
  3. 2026-05-28Add oQ8 MLX model99496c6948 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