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

mradermacher/Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic-GGUF

mradermacher Qwen 40B GGUF second-order 262K ctx
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%2FQwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic-GGUF"
Response includes
  • classification m3
  • files 15
  • hub_downloads_all_time 1,858
  • author_summary 3324 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 · lifetime
2K
1K last 30d - active
Likes
0
Model age
8w ago
created 2026-08-14
Downloads over time
Now2.4K→from854↑179%
7771.4K2K2.5K854 on Aug 192.4K on Oct 11AugSepOct
Aug 19 → Oct 11 · 48 snapshots · spans 53 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 · 2K 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 zh
Quantizations
IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf MTP fine tune heretic uncensored abliterated multi-stage tuned. all use cases thinking reasoning qwen3.6

Related

Total size
254 GB
Files
15
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-10-08 11:03

Files by quantization

Q8_0 2 files 39.7 GB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q8_0.gguf 39.1 GB 779530b5 download
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.mmproj-Q8_0.gguf 600 MB 8a79f3c9 download
Q6_K 1 file 30.2 GB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q6_K.gguf 30.2 GB 95e3be6b download
Q5_K 2 files 51.7 GB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q5_K_M.gguf 26.3 GB b58d04c0 download
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q5_K_S.gguf 25.5 GB eca664ba download
Q4_K 2 files 43.7 GB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q4_K_M.gguf 22.5 GB fec58465 download
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q4_K_S.gguf 21.2 GB f772497e download
IQ4 1 file 20.6 GB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.IQ4_XS.gguf 20.6 GB b50ecd7e download
Q3_K 3 files 53.8 GB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q3_K_L.gguf 19.5 GB b5b37892 download
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q3_K_M.gguf 18.0 GB c2200379 download
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q3_K_S.gguf 16.3 GB e1dab550 download
Q2_K 1 file 14.4 GB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.Q2_K.gguf 14.4 GB 139e2562 download
F16 1 file 885 MB
Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic.mmproj-f16.gguf 885 MB 8dc5dda2 download
Auxiliary files 2 files 8.08 KB
README.md 5.18 KB 57568810 download
.gitattributes 2.90 KB 63b4047e download

README current version from Hugging Face


base_model: DavidAU/Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic
language:

  • en
  • zh
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • MTP
  • fine tune
  • heretic
  • uncensored
  • abliterated
  • multi-stage tuned.
  • all use cases
  • thinking
  • reasoning
  • qwen3.6
  • coder
  • creative
  • writing
  • fiction
  • roleplaying
  • bfloat16
  • all use cases

About

static quants of https://huggingface.co/DavidAU/Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3.6-40B-Grand-Intelligence-Fable-Fusion-Uncensored-Heretic-i1-GGUF

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 15.6
GGUF Q3_K_S 17.6
GGUF Q3_K_M 19.4 lower quality
GGUF Q3_K_L 21.0
GGUF IQ4_XS 22.3
GGUF Q4_K_S 22.8 fast, recommended
GGUF Q4_K_M 24.3 fast, recommended
GGUF Q5_K_S 27.4
GGUF Q5_K_M 28.3
GGUF Q6_K 32.5 very good quality
GGUF Q8_0 42.1 fast, best quality

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. 2026-10-08auto-patch README.md8feec6c5.4 KB
    Loading...
  2. 2026-08-14auto-patch README.md394c5a35.2 KB
    Loading...
  3. 2026-08-14auto-patch README.md3d706bf5.3 KB
    Loading...
  4. 2026-08-14auto-patch README.md02b776c5 KB
    Loading...
  5. 2026-08-14uploaded from nico15446aae413 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