← back to catalog · registered 2026-11-16 00:03

DavidAU/Qwen3.5-9B-The-Defiant-2.0-Fable-701-876-Uncensored-Heretic-ZERO-NEO-IMATRIX-MAX-MTP-GGUF

DavidAU 9B GGUF 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/DavidAU%2FQwen3.5-9B-The-Defiant-2.0-Fable-701-876-Uncensored-Heretic-ZERO-NEO-IMATRIX-MAX-MTP-GGUF"
Response includes
  • classification m3
  • files 3
  • author_summary 231 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 · 30-day
0
Likes
1
Model age
6d ago
created 2026-11-15

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
Languages
ar zh en fr de hi id it ja ko pl pt ru es th vi
Tags
Regular GGUFS MTP GGUFS NEO Imatrix fine tune unsloth heretic uncensored abliterated heretic 2.1 ARA multi-stage tuned. all use cases thinking

Related

Total size
0 B
Files
3
Quantizations
1
Registered
2026-11-16 00:03
Last updated on HF
2026-11-16 07:20

Files by quantization

Auxiliary files 3 files 4.03 MB
neo-dodge.gif 4.02 MB ******** download
README.md 3.88 KB 42d7b52d download
.gitattributes 1.53 KB eaeb30e5 download

README current version from Hugging Face


language:

  • ar
  • zh
  • en
  • fr
  • de
  • hi
  • id
  • it
  • ja
  • ko
  • pl
  • pt
  • ru
  • es
  • th
  • vi
    license: apache-2.0
    tags:
  • MTP GGUFS
  • Regular GGUFS
  • NEO Imatrix
  • fine tune
  • unsloth
  • heretic
  • uncensored
  • abliterated
  • multi-stage tuned.
  • all use cases
  • thinking
  • reasoning
  • qwen3.5
  • coder
  • creative
  • writing
  • fiction
  • roleplaying
  • bfloat16
  • all use cases
    pipeline_tag: image-text-to-text
    base_model:
  • DavidAU/Qwen3.5-9B-The-Defiant-2.0-Fable-701-876-Uncensored-Heretic-ZERO-NEO-IMATRIX-MAX-MTP

[coming soon, final testing in progress... // Ultra low refusals: 4/100 with KLD: 0.0028 ("ZERO" effect on bench/model operation) via HERETIC 2.1 ARA. ]

[DavidAU] FOLLOW | ALL MODELS | COLLECTIONS | TRENDING | FAQs | SUPPORT
| Buy Me A Coffee (😁)

Going Nuclear: 701 ARC-C for both 8bit and 4bit. Model exceeds 7 of 7 benchmarks for Qwen 3.5 9B, Qwen3.5 27B, Qwen3.6 35B-A3B, and
Qwen 3.6 27B and it does so in 4bit and 8bit. Regular and MTP (fast) NEO IMATRIX GGUFs provided. (this model is part of the Qwen 3.6 27B Fable Fusion 711 pipelines: 2500+ likes, 4 million + downloads)

NEW - Qwen 3.8 Reasoning Modes: 2 MTP quants (Q6/Q8) Now with 5 reasoning modes (2 new - Spoon / Einstein), and 5
instruct modes (2 new - Spoon / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat"
(yes - model ctrl at the chat/message level). Model name has "plusIQ" in the name. A 12+12 (12 reasoning and 12 instruct) model
with interactive optimization/help system will be releasing shortly too. BF16/16-bit MTP GGUF also avail.
(there is also a extra robust "tools" version too - Q6 and Q8.)

Qwen3.5-9B-The-Defiant-2.0-Fable-701-876-Uncensored-Heretic-ZERO-NEO-IMATRIX-MAX-MTP-GGUF

BENCHMARKS:

          arc/c  arc/e boolq hswag obkqa piqa  wino

Qwen3.5-9B-The-Defiant-2.0-Fable-701-876-Uncensored-Heretic-ZERO-NEO-IMATRIX-MAX-MTP
bf16      0.703,0.875,0.905,0.774,0.526,0.805,0.725
mxfp8     0.701,0.876,0.904,0.775,0.528,0.805,0.726

Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic [instruct]
bf16      0.649,0.832,0.895,0.713,0.482,0.783,0.699
mxfp8     0.647,0.836,0.895,0.706,0.460,0.784,0.695
mxfp4     0.640,0.824,0.886,0.703,0.468,0.780,0.691

Qwen3.5-9B-Instruct: [base, non heretic]
mxfp8     0.571,0.719,0.895,0.683,0.426,0.770,0.671

---

Qwen3.8-27B:  [base, non heretic]
mxfp8     0.591,0.782,0.896,0.746,0.448,0.801,0.711
mxfp4     0.581,0.771,0.889,0.738,0.442,0.798,0.713

Qwen3.6-27B-Instruct: [base, non heretic]
mxfp8     0.647,0.803,0.910,0.773,0.450,0.806,0.742

Qwen3.5-27B-Instruct: [base, non heretic]
mxfp8     0.557,0.711,0.868,0.533,0.452,0.706,0.695

Qwen3.6-35B-A3B-Instruct [base, non heretic]
mxfp8     0.581,0.757,0.892,0.751,0.428,0.803,0.688

"Bench" NOTES:

  • Models are tested in "Instruct" mode because this generally works better with the testing harness.
  • Testing via "thinking" mode also shows the metrics (and changes) but not the true extent.
  • In actual fact when the model IS in thinking mode, it will exceed INSTRUCT benchmark scores in most cases.
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