supergemma4-26b-uncensored-v2
26BOtheruncensored
from google/gemma-4-26B-A4B-it
↓ 394K♥ 98442 repos
Qwable-3.6-27b-abliterated
Qwable-3.6-27b-abliterated is a refusal-ablated variant of Mia-AiLab/Qwable-3.6-27b, published on Hugging Face by huihui-ai. It is 27B parameters, 48GB VRAM class class and mit licence. It is distributed across 5 repositories in GGUF format, totalling 7.8K downloads.
Specification
- Model name
- Qwable-3.6-27b-abliterated
- Source repository
- huihui-ai/Huihui-Qwable-3.6-27b-abliterated-GGUF
- Base model
- Mia-AiLab/Qwable-3.6-27b
- Publisher
- huihui-ai
- Parameters
- 27B
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- mit
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 19 Jun 2026
- Last updated
- 15 Jul 2026
Ablation technique
How Qwable-3.6-27b-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
“This is an uncensored version of Mia-AiLab/Qwable-3.6-27b created with abliteration.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download huihui-ai/Huihui-Qwable-3.6-27b-abliterated-GGUF --local-dir ./qwable-3.6-27b-abliterated
llama-cli -m ./qwable-3.6-27b-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "huihui-ai/Huihui-Qwable-3.6-27b-abliterated-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve huihui-ai/Huihui-Qwable-3.6-27b-abliterated-GGUF --trust-remote-codeDownloads and variants (4)
Every published repository of Qwable-3.6-27b-abliterated, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| huihui-ai/Huihui-Qwable-3.6-27b-abliterated-GGUFsource | GGUF | 3.8K |
| coolthor/Huihui-Qwable-3.6-27b-abliterated-Q4_K_M-MTP-GGUF | GGUF | 2.7K |
| huihui-ai/Huihui-Qwable-3.6-27b-abliterated-MTP-GGUF | GGUF | 1.3K |
| cvgro/Huihui-Qwable-3.6-27b-abliterated-Q8-gguf | GGUF | 69 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwable-3.6-27b-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 Mia-AiLab/Qwable-3.6-27b, 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.
- Declared licence is mit, but the terms that bind you are Mia-AiLab/Qwable-3.6-27b’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 Qwable-3.6-27b-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 huihui-ai, and does not independently verify publisher claims. See responsible use.