ai.Qwen3-14B-abliterated
14BQwen
from huihui-ai/Qwen3-14B-abliterated
↓ 7.2K♥ 1
ai_Qwen3-14B-abliterated
ai_Qwen3-14B-abliterated is a refusal-ablated variant of huihui-ai/Qwen3-14B-abliterated, published on Hugging Face by bartowski. It is 14B parameters, 24GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 16.4K downloads.
Specification
- Model name
- ai_Qwen3-14B-abliterated
- Source repository
- bartowski/huihui-ai_Qwen3-14B-abliterated-GGUF
- Base model
- huihui-ai/Qwen3-14B-abliterated
- Publisher
- bartowski
- Parameters
- 14B
- Hardware class
- 10B – 25B — 24GB VRAM class
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 6 May 2025
- Last updated
- 6 May 2025
Ablation technique
How ai_Qwen3-14B-abliterated was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
Reported scope: Not stated by the publisher. Publishers frequently omit this, so verify behaviour empirically rather than assuming full coverage.
From the publisher’s model card
“All quants made using imatrix option with dataset from here”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download bartowski/huihui-ai_Qwen3-14B-abliterated-GGUF --local-dir ./ai-qwen3-14b-abliterated
llama-cli -m ./ai-qwen3-14b-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "bartowski/huihui-ai_Qwen3-14B-abliterated-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve bartowski/huihui-ai_Qwen3-14B-abliterated-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of ai_Qwen3-14B-abliterated.
| Repository | Format | Downloads |
|---|---|---|
| bartowski/huihui-ai_Qwen3-14B-abliterated-GGUFsource | GGUF | 16.4K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- ai_Qwen3-14B-abliterated will attempt offensive-security prompts that a hosted commercial model declines, which is what makes it usable for red-team corpus generation and for measuring what an unaligned model of this class produces.
- Capability is inherited from huihui-ai/Qwen3-14B-abliterated, not added by ablation — at 14B parameters, expect roughly the base model’s competence, minus some instruction-following fidelity.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- Declared licence is apache-2.0, but the terms that bind you are huihui-ai/Qwen3-14B-abliterated’s — a re-release cannot grant more than its parent.
Handling: run it isolated, put moderation in front of it if anyone outside your team can reach it, and verify the weights before loading — these are third-party artifacts. Full handling and licence guidance.
Metadata for ai_Qwen3-14B-abliterated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with bartowski, and does not independently verify publisher claims. See responsible use.