Qwen3.8-27B-abliterated
27BQwen
from Qwen/Qwen3.8-27B
↓ 3.9M♥ 1.7K166 repos
Qwen3.8-27B-Uncensored-ninfer5080-5070ti
Qwen3.8-27B-Uncensored-ninfer5080-5070ti is a abliterated and uncensored open-weight language model, published on Hugging Face by YukinoKaorisuna. It is 27B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in Transformers format, totalling 5.6K downloads.
Specification
- Model name
- Qwen3.8-27B-Uncensored-ninfer5080-5070ti
- Source repository
- YukinoKaorisuna/Qwen3.8-27B-Uncensored-ninfer5080-5070ti
- Base model
- Not declared
- Publisher
- YukinoKaorisuna
- Parameters
- 27B
- VRAM required
- ~17.2 GB at Q4_K_M, 4k context (estimated) — runs on 24 GB cards
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- 8K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- Transformers
- First indexed
- 25 Sept 2026
- Last updated
- 27 Sept 2026
Ablation technique
How Qwen3.8-27B-Uncensored-ninfer5080-5070ti was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“Qwen3.8-27B 的社区破限版，量化配方 groupwise-int-5080（Q3/Q4/Q5 混合，15.33 GB），适配 16GB 显存的 RTX 5070 Ti / 5080。”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "YukinoKaorisuna/Qwen3.8-27B-Uncensored-ninfer5080-5070ti"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve YukinoKaorisuna/Qwen3.8-27B-Uncensored-ninfer5080-5070ti --trust-remote-codeDownloads and variants (1)
The only published repository of Qwen3.8-27B-Uncensored-ninfer5080-5070ti.
| Repository | Format | Downloads |
|---|---|---|
| YukinoKaorisuna/Qwen3.8-27B-Uncensored-ninfer5080-5070tisource | Transformers | 5.6K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.8-27B-Uncensored-ninfer5080-5070ti 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 its base model, not added by ablation — at 27B 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
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 Qwen3.8-27B-Uncensored-ninfer5080-5070ti is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with YukinoKaorisuna, and does not independently verify publisher claims. See responsible use.