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

mradermacher/Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved-GGUF

mradermacher Qwen 9B 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%2FQwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved-GGUF"
Response includes
  • classification m3
  • files 16
  • hub_downloads_all_time 1,461
  • 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
1K
899 last 30d - active
Likes
0
Model age
2mo ago
created 2026-08-01
Downloads over time
Now1.8K→from0↑0%
06631.3K2K0 on Jul 291.8K on Oct 11JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 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 · 1K 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 JLENS Jacobian-Lens uncensored manual-abliteration conversational qwen3_5 experimental NSFW very_very_naughty j-wash

Related

Total size
77.8 GB
Files
16
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-10-09 15:50

Files by quantization

F16 2 files 18.0 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.f16.gguf 17.1 GB e6e31b3c download
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.mmproj-f16.gguf 876 MB 15456261 download
Q8_0 2 files 9.70 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q8_0.gguf 9.11 GB 0d91c1fd download
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.mmproj-Q8_0.gguf 595 MB 03eee1fd download
Q6_K 1 file 7.04 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q6_K.gguf 7.04 GB ecfef923 download
Q5_K 2 files 12.2 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q5_K_M.gguf 6.19 GB 4523801e download
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q5_K_S.gguf 6.03 GB b8425b7d download
Q4_K 2 files 10.5 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q4_K_M.gguf 5.38 GB f4c67ff3 download
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q4_K_S.gguf 5.11 GB f6179e9a download
IQ4 1 file 4.99 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.IQ4_XS.gguf 4.99 GB 64a122af download
Q3_K 3 files 13.2 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q3_K_L.gguf 4.70 GB a55761c2 download
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q3_K_M.gguf 4.41 GB e5442af5 download
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q3_K_S.gguf 4.06 GB 43d59fb8 download
Q2_K 1 file 3.65 GB
Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved.Q2_K.gguf 3.65 GB f2bc2467 download
Auxiliary files 2 files 8.33 KB
README.md 5.35 KB 2c1db860 download
.gitattributes 2.99 KB 1b2c3bbc download

README current version from Hugging Face


base_model: llmfan46/Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved
language:

  • en
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • JLENS
  • Jacobian-Lens
  • uncensored
  • manual-abliteration
  • conversational
  • qwen3_5
  • experimental
  • NSFW
  • very_very_naughty
  • j-wash
  • heretic
  • uncensored
  • decensored
  • abliterated

About

static quants of https://huggingface.co/llmfan46/Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3.5-9B-Nikusui-v1-Uncensored-Heretic-Native-MTP-Preserved-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 4.0
GGUF Q3_K_S 4.5
GGUF Q3_K_M 4.8 lower quality
GGUF Q3_K_L 5.1
GGUF IQ4_XS 5.5
GGUF Q4_K_S 5.6 fast, recommended
GGUF Q4_K_M 5.9 fast, recommended
GGUF Q5_K_S 6.6
GGUF Q5_K_M 6.7
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 4 versions

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

  1. 2026-10-09auto-patch README.md160ce9b5.6 KB
    Loading...
  2. 2026-08-01auto-patch README.md9a02a935.3 KB
    Loading...
  3. 2026-08-01auto-patch README.mdde421475.4 KB
    Loading...
  4. 2026-08-01uploaded from nico19a3e857413 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