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

SpaceTimee/Suri-Qwen-3.1-30B-Uncensored

SpaceTimee Qwen 31B MoE
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-3.1-30B-Uncensored"
Response includes
  • classification m-uncensored
  • files 27
  • benchmarks 16 entries
  • hub_downloads_all_time 715
  • 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
715
30 last 30d - cooling
Likes
1
Descendants
3
in 3 direct forks
Model age
7mo ago
created 2026-03-02

Training datasets

2 of 3 in /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.

NobodyExistsOnTheInternet/ToxicQAFinal Orion-zhen/dpo-toxic-zh heal unalignment/toxic-dpo-v0.2 heal
Downloads over time
Now726→from430↑69%
415529642756430 on Mar 4726 on Oct 11MarAprMayJunJulAugSepOct
Mar 4 → Oct 11 · 71 snapshots · spans 221 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
Arena-Battles 9190 LM-Arena
LM Arena Elo 1381.0765351051687 LM-Arena
Arena-Elo-Lower 1374.5507010142167 LM-Arena
Arena-Elo-Upper 1387.602369196121 LM-Arena
Arena-Rank 22 LM-Arena
Entertainment 1.3 UGI
Hazardous 3.5 UGI
Natural Intelligence 16.01 UGI
Political lean -28.3% UGI
Sensitive-Info 20.31 UGI
SocPol 1.7 UGI
UGI 26.87 UGI
Willingness (10) 4 UGI
W10-Adherence 4 UGI
W10-Direct 4 UGI
Writing 27.89 UGI

Genealogy 3 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/Qwen3-30B-A3B-Instruct-2507 this lineage
SpaceTimee/Suri-Qwen-3.1-30B-Uncensored↓ 30 3 forks
mradermacher/Suri-Qwen-3.1-30B-Uncensored-i1-GGUF↓ 948
SpaceTimee/Suri-Qwen-3.1-30B-Uncensored-GGUF↓ 305
mradermacher/Suri-Qwen-3.1-30B-Uncensored-GGUF↓ 206

Variants by this author 2 formats · 335 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Languages
zh en
Tags
transformers safetensors qwen3_moe text-generation suri qwen 30B uncensored unaligned text-generation-inference qwen3 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-Qwen3-30B-A3B-Instruct-2507-abliterated 17K
Total size
56.9 GB
Files
27
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-07 08:40
Source huggingface.co/SpaceTimee/Suri-Qwen-3.1-30B-Uncensored ↗ Base model Qwen/Qwen3-30B-A3B-Instruct-2507 ↗

Files by quantization

Auxiliary files 27 files 56.9 GB
model-00007-of-00016.safetensors 3.73 GB e54f4d03 download
model-00009-of-00016.safetensors 3.73 GB fb6208ba download
model-00011-of-00016.safetensors 3.73 GB 32fce582 download
model-00005-of-00016.safetensors 3.73 GB 524eaac4 download
model-00006-of-00016.safetensors 3.73 GB 4483b953 download
model-00010-of-00016.safetensors 3.73 GB a5afdecc download
model-00014-of-00016.safetensors 3.73 GB b969c044 download
model-00015-of-00016.safetensors 3.73 GB 63f48720 download
model-00013-of-00016.safetensors 3.73 GB e22128e3 download
model-00004-of-00016.safetensors 3.73 GB 153b44ca download
model-00002-of-00016.safetensors 3.73 GB 5cd126a0 download
model-00001-of-00016.safetensors 3.72 GB 81542aa7 download
model-00008-of-00016.safetensors 3.72 GB ea0d02d8 download
model-00003-of-00016.safetensors 3.72 GB 0b2a7010 download
model-00012-of-00016.safetensors 3.71 GB 725740bf download
model-00016-of-00016.safetensors 1.01 GB cece3ac4 download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
model.safetensors.index.json 1.62 MB 52b3fc91 download
merges.txt 1.59 MB 31349551 download
tokenizer_config.json 9.39 KB 16e2d364 download
chat_template.jinja 3.91 KB a31cebf5 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.04 KB da389aff download
README.md 780 B dbd8ca3b download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 614 B 9b8043f1 download

README current version from Hugging Face

datasets:

  • NobodyExistsOnTheInternet/ToxicQAFinal
  • Orion-zhen/dpo-toxic-zh
  • unalignment/toxic-dpo-v0.2
    language:
  • zh
  • en
    base_model:
  • Qwen/Qwen3-30B-A3B-Instruct-2507
  • unsloth/Qwen3-30B-A3B-Instruct-2507
    tags:
  • suri
  • qwen
  • 30B
  • uncensored
  • unaligned
  • text-generation-inference
  • qwen3
    pipeline_tag: text-generation
    library_name: transformers

Suri ⬡ Qwen

Uncensor Is All You Need


自我介绍

Suri Qwen 3.1 30B Uncensored: 一只基于 Qwen3 30B A3B Instruct 2507 的无审查 (去对齐) 模型

推荐参数

  • Temperature: 0.5 ~ 0.6
  • Top_P: 0.9 ~ 0.95
  • Presence_Penalty: 0 ~ 2

开发者

Space Time

联系方式

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

•ᴗ•

README history 6 versions

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

  1. 2026-03-07Update README.md4dd3bc2780 B
    Loading...
  2. 2026-03-07Update README.md6871b21780 B
    Loading...
  3. 2026-03-06Update README.md048060d660 B
    Loading...
  4. 2026-03-06Update README.mda217055662 B
    Loading...
  5. 2026-03-06Update README.md52eccca652 B
    Loading...
  6. 2026-03-02Unsloth Model Card4a9dc07605 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