← back to catalog · registered 2026-11-18 01:04

mradermacher/Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-GGUF

mradermacher 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/mradermacher%2FQwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic-GGUF"
Response includes
  • classification m3
  • files 16
  • author_summary 3602 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
1K
Likes
0
Model age
4d ago
created 2026-11-18
Downloads over time
Now 1.1K → from 0 ↑ 0%
04208401.3K 0 on Nov 18 1.1K on Nov 22 Nov
Nov 18 → Nov 22 · 5 snapshots · spans 4 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.

Variants by this author 2 formats · 4K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Languages
en
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf merge della heretic abliterated uncensored decensored qwen3.5 qwen llama.cpp vision

Related

Total size
77.8 GB
Files
16
Quantizations
9
Registered
2026-11-18 01:04
Last updated on HF
2026-11-18 07:18

Files by quantization

F16 2 files 18.0 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.f16.gguf 17.1 GB cafd0e50 download
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.mmproj-f16.gguf 876 MB c14fff49 download
Q8_0 2 files 9.70 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q8_0.gguf 9.11 GB 7384a052 download
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.mmproj-Q8_0.gguf 595 MB 94a814e1 download
Q6_K 1 file 7.04 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q6_K.gguf 7.04 GB 8d91c38a download
Q5_K 2 files 12.2 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q5_K_M.gguf 6.19 GB 0aa574c3 download
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q5_K_S.gguf 6.03 GB 17003e27 download
Q4_K 2 files 10.5 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q4_K_M.gguf 5.38 GB f389d75d download
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q4_K_S.gguf 5.11 GB a8365dbc download
IQ4 1 file 4.99 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.IQ4_XS.gguf 4.99 GB 8b7fff38 download
Q3_K 3 files 13.2 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q3_K_L.gguf 4.70 GB 58e8716c download
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q3_K_M.gguf 4.41 GB 91ad42ae download
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q3_K_S.gguf 4.06 GB 60596a7e download
Q2_K 1 file 3.65 GB
Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic.Q2_K.gguf 3.65 GB bcb90e14 download
Auxiliary files 2 files 6.80 KB
README.md 4.08 KB 630d09da download
.gitattributes 2.73 KB 343422d5 download

README current version from Hugging Face


base_model: spale04/Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic
language:

  • en
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • gguf
  • merge
  • della
  • heretic
  • abliterated
  • uncensored
  • decensored
  • qwen3.5
  • qwen
  • llama.cpp
  • vision
  • reasoning

About

static quants of https://huggingface.co/spale04/Qwopus-JOSIE-Qwen3.5-9B-UNCENSORED-heretic

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs
for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
GGUF mmproj-Q8_0 0.7 multi-modal supplement
GGUF mmproj-f16 1.0 multi-modal supplement
GGUF Q2_K 4.0
GGUF Q3_K_S 4.5
GGUF Q3_K_M 4.8 lower quality
GGUF Q4_K_S 5.6 fast, recommended
GGUF Q4_K_M 5.9 fast, recommended
GGUF Q6_K 7.7 very good quality
GGUF Q8_0 9.9 fast, best quality
GGUF f16 18.5 16 bpw, overkill

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

README history 5 versions

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

  1. 2026-11-18 auto-patch README.md b958fa0 4.7 KB
    Loading...
  2. 2026-11-18 auto-patch README.md d677c66 4.8 KB
    Loading...
  3. 2026-11-18 auto-patch README.md e3b9e2e 4.1 KB
    Loading...
  4. 2026-11-18 auto-patch README.md 313a9d4 3 KB
    Loading...
  5. 2026-11-18 uploaded from rich1 ce482e3 393 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