Offrail-27B-Uncensored
27BOtheruncensored
from OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF
↓ 20.2K♥ 28
Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer
Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer is a Heretic-ablated variant of OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF, published on Hugging Face by emiltsoi. It is 27B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 2 repositories in Transformers format, totalling 38.6K downloads.
Specification
- Model name
- Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer
- Source repository
- emiltsoi/Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer
- Publisher
- emiltsoi
- 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
- Image text to text
- Context window
- 1024K 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 Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer was modified, and what that implies.
Heretic
Automated directional ablation via the Heretic toolchain, which searches for the refusal direction and applies it with a KL-divergence budget so general capability is preserved.
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
“A native NInfer artifact (.ninfer) of the Heretic-decensored Ternary Bonsai 2 27B — the uncensored variant, packaged for the consolidated NInfer engine with DFlash2 speculative decoding, MTP, and the Qwen3.8-27B vision tower in a single file.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "emiltsoi/Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve emiltsoi/Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer --trust-remote-codeDownloads and variants (1)
The only published repository of Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer.
| Repository | Format | Downloads |
|---|---|---|
| emiltsoi/Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfersource | Transformers | 38.6K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer 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 OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF, 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 apache-2.0, but the terms that bind you are OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF’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 Ternary-Bonsai-2-27B-Uncensored-Heretic-NInfer is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with emiltsoi, and does not independently verify publisher claims. See responsible use.