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

SpaceTimee/Suri-Qwen-3.5-4B-Uncensored-Preview

SpaceTimee Qwen 4.7B multimodal
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/SpaceTimee%2FSuri-Qwen-3.5-4B-Uncensored-Preview"
Response includes
  • classification m-uncensored
  • files 10
  • benchmarks 11 entries
  • hub_downloads_all_time 389
  • author_summary 31 models
  • readme_text full
Try next
GET/models?author=SpaceTimee
All 31 models by SpaceTimee
 GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
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
389
39 last 30d - stable
Likes
1
Descendants
4
in 4 direct forks
Model age
7mo ago
created 2026-03-05

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.

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
Downloads over time
Now402→from230↑75%
221287353419230 on Mar 18402 on Oct 11402 on Oct 8MarAprMayJunJulAugSepOct
Mar 18 → Oct 11 · 69 snapshots · spans 207 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 0.9 UGI
Hazardous 1.2 UGI
Natural Intelligence 13.45 UGI
Political lean -17.3% UGI
Sensitive-Info 11.73 UGI
SocPol 1.5 UGI
UGI 15.32 UGI
Willingness (10) 2.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 3 UGI
Writing 29.68 UGI

Genealogy 4 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.

Qwen/Qwen3.5-4B this lineage
SpaceTimee/Suri-Qwen-3.5-4B-Uncensored-Preview↓ 39 4 forks
mradermacher/Suri-Qwen-3.5-4B-Uncensored-Low-i1-GGUF↓ 1,184
mradermacher/Suri-Qwen-3.5-4B-Uncensored-i1-GGUF↓ 1,133
mradermacher/Suri-Qwen-3.5-4B-Uncensored-GGUF↓ 1,087
mradermacher/Suri-Qwen-3.5-4B-Uncensored-Low-GGUF↓ 786

Metadata

Languages
zh en
Tags
transformers safetensors qwen3_5 image-text-to-text suri qwen 4B uncensored unaligned text-generation-inference qwen3.5 conversational

Related

Other by SpaceTimee
Suri-Qwen-3.8-27B-Uncensored-GGUF 13K Suri-Qwen-3.5-4B-Uncensored-GGUF 1K Suri-Qwen-3.5-9B-Uncensored-GGUF 1K Suri-Qwen-3.5-27B-Uncensored-GGUF 883 Suri-Qwen-3.8-27B-Uncensored-MLX 777
Same base model
huihui-ai/Huihui-Qwen3.5-4B-abliterated 8K insraq/Qwen3.5-4B-EmperoAI-Qwen3.8-Distill-Heretic-Abliterated-MTP-GGUF 6K Andycurrent/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive 3K rodrigomt/Qwen3.5-4B-Uncensored-Aggressive 2K DreamFast/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Safetensor-Benchmark 1K
Total size
8.68 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-04-14 06:00
Source huggingface.co/SpaceTimee/Suri-Qwen-3.5-4B-Uncensored-Preview ↗ Base model Qwen/Qwen3.5-4B ↗

Files by quantization

Auxiliary files 10 files 8.69 GB
model.safetensors-00001-of-00002.safetensors 4.96 GB 36274ecb download
model.safetensors-00002-of-00002.safetensors 3.72 GB 219cc5e2 download
tokenizer.json 12.2 MB 5f9e4d49 download
model.safetensors.index.json 74.4 KB fddda603 download
tokenizer_config.json 16.3 KB eda48d3e download
chat_template.jinja 7.57 KB a585dec8 download
config.json 3.39 KB 5d19307b download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.27 KB 7ad6acdf download
README.md 1.04 KB f89b62bf download

README current version from Hugging Face

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
    base_model:
  • Qwen/Qwen3.5-4B
  • unsloth/Qwen3.5-4B
    tags:
  • suri
  • qwen
  • 4B
  • uncensored
  • unaligned
  • text-generation-inference
  • qwen3.5
    pipeline_tag: image-text-to-text
    library_name: transformers
    new_version: SpaceTimee/Suri-Qwen-3.5-4B-Uncensored

Suri ⬡ Qwen

Uncensor Is All You Need


自我介绍

Suri Qwen 3.5 4B Uncensored Preview: 一只基于 Qwen3.5 4B 的无审查 (去对齐) 模型

该模型为主模型 Suri Qwen 3.5 4B Uncensored 训练完成前的临时模型，与主模型相比质量更差，建议优先使用主模型

推荐参数

  • Temperature: 0.6 ~ 1.0
  • Top_P: 0.8 ~ 0.95
  • Repetition_Penalty: 1.1

开发者

Space Time

联系方式

  1. QQ 群: 902575634
  2. 邮箱: [email protected]

•ᴗ•

README history 8 versions

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

  1. 2026-04-14Update README.md9f0b9bb1 KB
    Loading...
  2. 2026-03-16Update README.mde40704c1 KB
    Loading...
  3. 2026-03-16Update README.mdec15d6c1.1 KB
    Loading...
  4. 2026-03-07Update README.mdef2609d1 KB
    Loading...
  5. 2026-03-06Update README.md036cdbe912 B
    Loading...
  6. 2026-03-06Update README.md5af8997909 B
    Loading...
  7. 2026-03-06Update README.md8ab1ce8899 B
    Loading...
  8. 2026-03-05Unsloth Model Cardbf83010607 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.

Get the app Browse the catalog
Open in Abliteration