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

xCloudinfo/Qwen3.6-35B-A3B-Uncensored-xCloud-GGUF

xCloudinfo Qwen 35B GGUF MoE second-order
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/xCloudinfo%2FQwen3.6-35B-A3B-Uncensored-xCloud-GGUF"
Response includes
  • classification m8
  • files 4
  • author_summary 25 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
MEDIUM
Inherited from base model
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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 · 30-day
3K
↑ 4,729% in 90 days
Likes
0
Model age
4mo ago
created 2026-06-14
Downloads over time
Now4.1K→from85↑4,729%
01.5K3K4.5K85 on Jun 174.1K on Aug 294.1K on Aug 26JunJulAug
Jun 17 → Aug 29 · 13 snapshots · spans 73 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 · 3K 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 multilingual
Quantizations
Q4_K Q6_K
Tags
gguf qwen3.6 moe llama-cpp abliterated uncensored xcloudinfo text-generation en zh multilingual base_model:xCloudinfo/Qwen3.6-35B-A3B-Uncensored-xCloud

Related

Total size
46.3 GB
Files
4
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2026-06-23 16:20

Files by quantization

Q6_K 1 file 26.6 GB
Qwen3.6-35B-A3B-Uncensored-xCloud-Q6_K.gguf 26.6 GB e9c65a65 download
Q4_K 1 file 19.7 GB
Qwen3.6-35B-A3B-Uncensored-xCloud-Q4_K_M.gguf 19.7 GB 7d59ed87 download
Auxiliary files 2 files 3.28 KB
.gitattributes 1.64 KB 023e387a download
README.md 1.63 KB af88773a download

README current version from Hugging Face


license: apache-2.0
base_model: xCloudinfo/Qwen3.6-35B-A3B-Uncensored-xCloud
language:

  • en
  • zh
  • multilingual
    tags:
  • qwen3.6
  • moe
  • gguf
  • llama-cpp
  • abliterated
  • uncensored
  • xcloudinfo
    pipeline_tag: text-generation

Qwen3.6-35B-A3B-Uncensored-xCloud-GGUF

云碩科技 · xCloudinfo · 系列:無審查 · Abliterated / Uncensored

⚠️ 經 abliteration(aggressive) 處理,會比原版更少拒答。請僅在你被授權的範圍內使用。

xCloudinfo/Qwen3.6-35B-A3B-Uncensored-xCloud 的 GGUF(llama.cpp / Ollama) 量化版本。

檔案 量化 大小
…-Q6_K.gguf Q6_K(接近無損) ≈ 28 GB
…-Q4_K_M.gguf Q4_K_M(部署首選) ≈ 21 GB

純文字 GGUF(不含 mmproj)。需要圖文請用 merged safetensors 版。

用法

llama-server -m Qwen3.6-35B-A3B-Uncensored-xCloud-Q4_K_M.gguf -c 8192 -ngl 99

原理

依 Arditi et al. (2024),以權重正交化移除殘差流拒絕方向(91 矩陣含 256-expert MoE、strength 1.0),不重訓。詳見 merged 版模型卡。

用途與責任

  • 設計用途:降低過度拒絕,供授權範圍內研究與應用。
  • 已移除安全拒絕傾向,使用者須自行加上安全防護與輸出審查,並對用途與後果負完全責任;不得用於有害或違法用途。

授權與來源


由 云碩科技 xCloudinfo 於自有 AI 算力資源池製作。

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