← back to catalog · registered 2026-11-19 22:04

mradermacher/Qwen3.5-0.8B-Heretic-Uncensored-GGUF

mradermacher 800M 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%2FQwen3.5-0.8B-Heretic-Uncensored-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
1
Model age
2d ago
created 2026-11-19
Downloads over time
Now 1.2K → from 0 ↑ 0%
04478951.3K 0 on Nov 19 1.2K on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 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 · 5K 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 qwen qwen3.5 qwen3_5 multimodal vision-language conversational safetensors heretic uncensored decensored

Related

Total size
6.94 GB
Files
16
Quantizations
9
Registered
2026-11-19 22:04
Last updated on HF
2026-11-19 23:34

Files by quantization

F16 2 files 1.60 GB
Qwen3.5-0.8B-Heretic-Uncensored.f16.gguf 1.41 GB b6009a3e download
Qwen3.5-0.8B-Heretic-Uncensored.mmproj-f16.gguf 195 MB e45d0e1c download
Q8_0 2 files 885 MB
Qwen3.5-0.8B-Heretic-Uncensored.Q8_0.gguf 774 MB 735a5736 download
Qwen3.5-0.8B-Heretic-Uncensored.mmproj-Q8_0.gguf 111 MB ba56bf55 download
Q6_K 1 file 601 MB
Qwen3.5-0.8B-Heretic-Uncensored.Q6_K.gguf 601 MB ddb885f8 download
Q5_K 2 files 1.06 GB
Qwen3.5-0.8B-Heretic-Uncensored.Q5_K_M.gguf 551 MB e08c111c download
Qwen3.5-0.8B-Heretic-Uncensored.Q5_K_S.gguf 538 MB b3c916ba download
Q4_K 2 files 987 MB
Qwen3.5-0.8B-Heretic-Uncensored.Q4_K_M.gguf 505 MB b1eef814 download
Qwen3.5-0.8B-Heretic-Uncensored.Q4_K_S.gguf 482 MB 2924179f download
IQ4 1 file 482 MB
Qwen3.5-0.8B-Heretic-Uncensored.IQ4_XS.gguf 482 MB e42d7e40 download
Q3_K 3 files 1.30 GB
Qwen3.5-0.8B-Heretic-Uncensored.Q3_K_L.gguf 469 MB f37007ad download
Qwen3.5-0.8B-Heretic-Uncensored.Q3_K_M.gguf 445 MB ea344e4b download
Qwen3.5-0.8B-Heretic-Uncensored.Q3_K_S.gguf 415 MB b39d86ef download
Q2_K 1 file 403 MB
Qwen3.5-0.8B-Heretic-Uncensored.Q2_K.gguf 403 MB 66231650 download
Auxiliary files 2 files 7.15 KB
README.md 4.57 KB 2cf07ccd download
.gitattributes 2.58 KB 369d2998 download

README current version from Hugging Face


base_model: Peymandc/Qwen3.5-0.8B-Heretic-Uncensored
language:

  • en
    library_name: transformers
    license: apache-2.0
    license_link: https://huggingface.co/Qwen/Qwen3.5-0.8B/blob/main/LICENSE
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • qwen
  • qwen3.5
  • qwen3_5
  • multimodal
  • vision-language
  • conversational
  • transformers
  • safetensors
  • heretic
  • uncensored
  • decensored
  • abliterated
  • reproducible

About

static quants of https://huggingface.co/Peymandc/Qwen3.5-0.8B-Heretic-Uncensored

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 0.2 multi-modal supplement
GGUF mmproj-f16 0.3 multi-modal supplement
GGUF Q2_K 0.5
GGUF Q3_K_S 0.5
GGUF Q3_K_M 0.6 lower quality
GGUF Q3_K_L 0.6
GGUF Q4_K_S 0.6 fast, recommended
GGUF IQ4_XS 0.6
GGUF Q4_K_M 0.6 fast, recommended
GGUF Q5_K_S 0.7
GGUF Q5_K_M 0.7
GGUF Q6_K 0.7 very good quality
GGUF Q8_0 0.9 fast, best quality
GGUF f16 1.6 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 3 versions

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

  1. 2026-11-19 auto-patch README.md 85bb748 4.5 KB
    Loading...
  2. 2026-11-19 auto-patch README.md 1422f02 4.6 KB
    Loading...
  3. 2026-11-19 uploaded from back eaec179 383 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