Qwen3.8-27B-Uncensored-YMQ
27BQwenuncensored
from JonathanColetti/Qwen3.8-27B-Uncensored
↓ 156.5K♥ 912 repos
Qwen3.8-27B-Unleashed
Qwen3.8-27B-Unleashed is a abliterated and uncensored variant of JonathanColetti/Qwen3.8-27B-Uncensored, published on Hugging Face by outsourc-e. It is 27B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 4 repositories in GGUF format, totalling 83.8K downloads.
Specification
- Model name
- Qwen3.8-27B-Unleashed
- Source repository
- outsourc-e/Qwen3.8-27B-Unleashed-GGUF
- Base model
- JonathanColetti/Qwen3.8-27B-Uncensored
- Publisher
- outsourc-e
- Parameters
- 27B
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- 64K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 20 Aug 2026
- Last updated
- 30 Aug 2026
Ablation technique
How Qwen3.8-27B-Unleashed 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
“Most uncensored GGUFs are uniform quants — every layer gets the same treatment. These use a per-tensor type map, so sensitive tensors keep precision while tolerant ones compress hard. The result: a Q3 that outperforms a Q4 3.3 GB larger, with full 250k-token retrieval.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download outsourc-e/Qwen3.8-27B-Unleashed-GGUF --local-dir ./qwen3.8-27b-unleashed
llama-cli -m ./qwen3.8-27b-unleashed/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "outsourc-e/Qwen3.8-27B-Unleashed-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve outsourc-e/Qwen3.8-27B-Unleashed-GGUF --trust-remote-codeDownloads and variants (3)
Every published repository of Qwen3.8-27B-Unleashed, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| outsourc-e/Qwen3.8-27B-Unleashed-GGUFsource | GGUF | 81.8K |
| AleaiactaEst1/Qwen3.8-27B-Unleashed-GGUF | GGUF | 1.1K |
| SwagMessiah100/Qwen3.8-27B-Unleashed-GGUF | GGUF | 944 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.8-27B-Unleashed 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 JonathanColetti/Qwen3.8-27B-Uncensored, 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.
- Declared licence is apache-2.0, but the terms that bind you are JonathanColetti/Qwen3.8-27B-Uncensored’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 Qwen3.8-27B-Unleashed is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with outsourc-e, and does not independently verify publisher claims. See responsible use.