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

UnstableLlama/DavidAU_Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-3.00bpw-exl3

UnstableLlama Qwen 7.3B 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/UnstableLlama%2FDavidAU_Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-3.00bpw-exl3"
Response includes
  • classification m3
  • files 15
  • hub_downloads_all_time 136
  • author_summary 9 models
  • readme_text full
Try next
GET/models?author=UnstableLlama
All 9 models by UnstableLlama
 GET/models?family=qwen&method=m3
Sibling qwen 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
136
20 last 30d - stable
Likes
0
Model age
6mo ago
created 2026-04-02
Downloads over time
Now146→from28↑421%
226711315828 on Apr 15146 on Oct 11146 on Oct 10AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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.

DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking↓ 270 this lineage
UnstableLlama/DavidAU_Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-3.00bpw-exl3↓ 20

Metadata

License
apache-2.0
Tags
safetensors qwen3_5 exl3 base_model:DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking base_model:quantized:DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking license:apache-2.0 3-bit region:us

Related

Other by UnstableLlama
gemma-4-31B-it-uncensored-heretic-exl3-8.00bpw 94 gemma-4-31B-it-uncensored-heretic-exl3-3.08bpw 33 Qwen3.5-27B-ultra-uncensored-heretic-v2-exl3-6.00bpw 28 Qwen3.5-27B-ultra-uncensored-heretic-v2-exl3-2.06bpw 27 DavidAU_Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-4.00bpw-exl3 25
Same base model
mradermacher/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-i1-GGUF 2K mradermacher/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-GGUF 912 zecanard/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-4bit-nvfp4 507 zecanard/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-2bit-int2-affine 244 TheCluster/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-mxfp4 231
Total size
17.0 GB
Files
15
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-02 03:10
Source huggingface.co/UnstableLlama/DavidAU_Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-3.00bpw-exl3 ↗ Base model DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking →

Files by quantization

Auxiliary files 15 files 17.0 GB
model-00001-of-00003.safetensors 7.99 GB 42cf2360 download
model-00002-of-00003.safetensors 7.22 GB bae11a72 download
model-00003-of-00003.safetensors 1.75 GB 3978c8f9 download
tokenizer.json 12.2 MB 5f9e4d49 download
vocab.json 6.41 MB 0aa0ce06 download
quantization_config.json 919 KB fd39e588 download
model.safetensors.index.json 331 KB cea93144 download
tokenizer_config.json 8.48 KB 3e0a1107 download
chat_template.jinja 7.78 KB 5a663a52 download
README.md 5.56 KB f5659e4a download
config.json 5.52 KB 6109ba20 download
.gitattributes 1.53 KB 52373fe2 download
preprocessor_config.json 390 B 2ea84a43 download
video_preprocessor_config.json 385 B 3ba673a5 download
DavidAU_Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-ThinkingMeasured.csv 154 B e4161c19 download

README current version from Hugging Face

license: apache-2.0
base_model: DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
base_model_relation: quantized
quantized_by: UnstableLlama
tags:

  • exl3

>> DavidAU / Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

[QUANTS BY :: UnstableLlama]
// Information
exl3 quantizations of DavidAU's Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking via exllamav3.

Repo generated automatically with ezexl3.
// Repo Data
REVISION GiB KL DIV PPL
3.00bpw 16.95 0.0336 6.7797
4.00bpw 21.20 0.0091 6.6965
bf16 73.64 0.0000 6.6668
// CLI Download
hf download UnstableLlama/Jackrong_Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-exl3 --revision "4.00bpw" --local-dir ./Jackrong_Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-exl3-4.00bpw

README history 1 version

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

  1. 2026-04-02Duplicate from UnstableLlama/DavidAU_Qwen3.5-40B-Claude-4.6-Opus-Deckard-Here...b337c615.6 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.

Get the app Browse the catalog
Open in Abliteration