← back to catalog · registered 2026-08-25 10:02

bowmanslayer/Qwen3.5-9B-Uncensored-GGUF

bowmanslayer 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/bowmanslayer%2FQwen3.5-9B-Uncensored-GGUF"
Response includes
  • classification m8
  • files 7
  • hub_downloads_all_time 3,668
  • author_summary 9 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 · lifetime
4K
Likes
1
Model age
6w ago
created 2026-08-25
Downloads over time
Now4.4K→from373↑1,080%
1721.7K3.3K4.8K373 on Aug 264.4K on Oct 11AugSepOct
Aug 26 → Oct 11 · 47 snapshots · spans 46 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 · 6K 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
Quantizations
BF16 IQ4 Q4_K Q5_K Q6_K
Tags
gguf uncensored abliterated qwen3.5 llama.cpp not-for-all-audiences en zh base_model:bowmanslayer/Qwen3.5-9B-Uncensored base_model:quantized:bowmanslayer/Qwen3.5-9B-Uncensored license:apache-2.0 endpoints_compatible

Related

Total size
40.7 GB
Files
7
Quantizations
6
Registered
2026-08-25 10:02
Last updated on HF
2026-08-25 10:42

Files by quantization

BF16 1 file 17.1 GB
Qwen3.5-9B-Uncensored-BF16.gguf 17.1 GB d41cb546 download
Q6_K 1 file 7.04 GB
Qwen3.5-9B-Uncensored-Q6_K.gguf 7.04 GB fa3afb89 download
Q5_K 1 file 6.19 GB
Qwen3.5-9B-Uncensored-Q5_K_M.gguf 6.19 GB 2b3418c2 download
Q4_K 1 file 5.38 GB
Qwen3.5-9B-Uncensored-Q4_K_M.gguf 5.38 GB 38865be9 download
IQ4 1 file 4.99 GB
Qwen3.5-9B-Uncensored-IQ4_XS.gguf 4.99 GB 309480a9 download
Auxiliary files 2 files 3.91 KB
README.md 2.09 KB bb9643ec download
.gitattributes 1.82 KB 175423a7 download

README current version from Hugging Face


library_name: gguf
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3.5-9B/blob/main/LICENSE
base_model:

  • bowmanslayer/Qwen3.5-9B-Uncensored
    base_model_relation: quantized
    tags:
  • uncensored
  • abliterated
  • qwen3.5
  • gguf
  • llama.cpp
    language:
  • en
  • zh

Qwen3.5-9B-Uncensored-GGUF

llama.cpp GGUF 量化,多档,基于
bowmanslayer/Qwen3.5-9B-Uncensored。

注意:GGUF 主要走 llama.cpp 侧,视觉塔转换 llama.cpp 现有支持通过 mmproj-*.gguf
配套文件实现(如已提供),否则本 GGUF 仅为文字侧推理使用。要用视觉能力请用主仓 bf16
或 W4A16 版本 + vLLM。

一、量化档次

文件 位深 大小 用途
Qwen3.5-9B-Uncensored-BF16.gguf bf16 ~18 GB 参考,GPU 24GB+
Qwen3.5-9B-Uncensored-Q8_0.gguf Q8_0 ~10 GB 近无损,16 GB+ GPU
Qwen3.5-9B-Uncensored-Q6_K.gguf Q6_K ~7.6 GB 高质量,12 GB+ GPU
Qwen3.5-9B-Uncensored-Q5_K_M.gguf Q5_K_M ~6.5 GB 平衡,12 GB GPU
Qwen3.5-9B-Uncensored-Q4_K_M.gguf Q4_K_M ~5.5 GB 激进,8 GB+ GPU
Qwen3.5-9B-Uncensored-IQ4_XS.gguf IQ4_XS ~5 GB 更小,8 GB GPU

二、llama.cpp 使用

推荐(开 int8 KV 拿到更大上下文):

./llama-server \
  -m Qwen3.5-9B-Uncensored-Q6_K.gguf \
  --ctx-size 32768 \
  --n-gpu-layers -1 \
  -ctk q8_0 -ctv q8_0 \
  --host 0.0.0.0 --port 8080

单条推理:

./llama-cli -m Qwen3.5-9B-Uncensored-Q6_K.gguf -p "Hello" \
  -n 512 --n-gpu-layers -1 -ctk q8_0 -ctv q8_0

三、和 vLLM W4A16 版本的选择

四、方法与限制

见主仓 bowmanslayer/Qwen3.5-9B-Uncensored。

五、署名

基座模型见 Qwen/Qwen3.5-9B,Apache 2.0。

README history 2 versions

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

  1. 2026-08-25README: bilingual + full eval + legal + gated + Q3_K_M row0d6b68016.7 KB
    Loading...
  2. 2026-08-25Upload README.md with huggingface_hubf32a16a2.1 KB
    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