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

mradermacher/Suri-Qwen-3.5-4B-Uncensored-Low-GGUF

mradermacher Qwen 4B 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%2FSuri-Qwen-3.5-4B-Uncensored-Low-GGUF"
Response includes
  • classification m8
  • files 16
  • hub_downloads_all_time 4,402
  • author_summary 3324 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=mradermacher (M8 quantization producer, never originator)
  • is_gguf=1
  • base_model='SpaceTimee/Suri-Qwen-3.5-4B-Uncensored-Preview' (base has 'abliterated' marker, assume M1 default)
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
4K
786 last 30d - stable
Likes
2
Model age
7mo ago
created 2026-03-07

Training datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now4.6K→from0↑0%
01.7K3.4K5.1K0 on Mar 44.6K on Oct 11MarAprMayJunJulAugSepOct
Mar 4 → Oct 11 · 71 snapshots · spans 221 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

Languages
zh en
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf suri qwen 4B uncensored unaligned text-generation-inference qwen3.5 zh en dataset:SpaceTimee/Suri-Dataset-1.0-Toxic-SFT-EN-Thinking

Related

Total size
36.0 GB
Files
16
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2026-03-16 12:14

Files by quantization

F16 2 files 8.47 GB
Suri-Qwen-3.5-4B-Uncensored-Low.f16.gguf 7.85 GB 57a9fe09 download
Suri-Qwen-3.5-4B-Uncensored-Low.mmproj-f16.gguf 641 MB c14239a4 download
Q8_0 2 files 4.52 GB
Suri-Qwen-3.5-4B-Uncensored-Low.Q8_0.gguf 4.17 GB d32ba498 download
Suri-Qwen-3.5-4B-Uncensored-Low.mmproj-Q8_0.gguf 350 MB e63f9727 download
Q6_K 1 file 3.23 GB
Suri-Qwen-3.5-4B-Uncensored-Low.Q6_K.gguf 3.23 GB 48236c06 download
Q5_K 2 files 5.68 GB
Suri-Qwen-3.5-4B-Uncensored-Low.Q5_K_M.gguf 2.90 GB 830dbcb1 download
Suri-Qwen-3.5-4B-Uncensored-Low.Q5_K_S.gguf 2.78 GB fe010fcc download
Q4_K 2 files 4.90 GB
Suri-Qwen-3.5-4B-Uncensored-Low.Q4_K_M.gguf 2.52 GB cc51fc57 download
Suri-Qwen-3.5-4B-Uncensored-Low.Q4_K_S.gguf 2.38 GB a0064fc5 download
IQ4 1 file 2.28 GB
Suri-Qwen-3.5-4B-Uncensored-Low.IQ4_XS.gguf 2.28 GB acc5ce06 download
Q3_K 3 files 6.23 GB
Suri-Qwen-3.5-4B-Uncensored-Low.Q3_K_L.gguf 2.20 GB 2dfd3250 download
Suri-Qwen-3.5-4B-Uncensored-Low.Q3_K_M.gguf 2.10 GB daeb293c download
Suri-Qwen-3.5-4B-Uncensored-Low.Q3_K_S.gguf 1.93 GB 943f7209 download
Q2_K 1 file 1.67 GB
Suri-Qwen-3.5-4B-Uncensored-Low.Q2_K.gguf 1.67 GB 9eb1f23a download
Auxiliary files 2 files 7.04 KB
README.md 4.46 KB a0782aef download
.gitattributes 2.58 KB 3f908a66 download

README current version from Hugging Face


base_model: SpaceTimee/Suri-Qwen-3.5-4B-Uncensored-Preview
datasets:

  • SpaceTimee/Suri-Dataset-1.0-Toxic-SFT-EN-Thinking
  • SpaceTimee/Suri-Dataset-1.0-Toxic-DPO-ZH-Thinking
  • SpaceTimee/Suri-Dataset-1.0-Toxic-DPO-EN-Thinking
    language:
  • zh
  • en
    library_name: transformers
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • suri
  • qwen
  • 4B
  • uncensored
  • unaligned
  • text-generation-inference
  • qwen3.5

About

static quants of https://huggingface.co/SpaceTimee/Suri-Qwen-3.5-4B-Uncensored-Preview

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Suri-Qwen-3.5-4B-Uncensored-Low-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 0.5 multi-modal supplement
GGUF mmproj-f16 0.8 multi-modal supplement
GGUF Q2_K 1.9
GGUF Q3_K_S 2.2
GGUF Q3_K_M 2.4 lower quality
GGUF Q3_K_L 2.5
GGUF IQ4_XS 2.6
GGUF Q4_K_S 2.7 fast, recommended
GGUF Q4_K_M 2.8 fast, recommended
GGUF Q5_K_S 3.1
GGUF Q5_K_M 3.2
GGUF Q6_K 3.6 very good quality
GGUF Q8_0 4.6 fast, best quality
GGUF f16 8.5 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. 2026-03-16auto-patch README.md6f2f7934.5 KB
    Loading...
  2. 2026-03-08auto-patch README.mdbc83e684.5 KB
    Loading...
  3. 2026-03-07auto-patch README.md41f68944.6 KB
    Loading...
  4. 2026-03-07auto-patch README.md1f7f2a82.6 KB
    Loading...
  5. 2026-03-07uploaded from nico19d6f105385 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