Ternary-Bonsai-2-27B-Uncensored-Heretic
27BOtherheretic
from prism-ml/Ternary-Bonsai-2-27B-gguf
↓ 131.1K♥ 1542 repos
Ternary-Bonsai-2-27B-Uncensored-Heretic-v2
Ternary-Bonsai-2-27B-Uncensored-Heretic-v2 is a Heretic-ablated variant of prism-ml/Ternary-Bonsai-2-27B-gguf, published on Hugging Face by OS-Software. It is 27B parameters, 48GB VRAM class class and apache-2.0 licence. It is distributed across 3 repositories in GGUF and MLX formats, totalling 64K downloads.
Specification
- Model name
- Ternary-Bonsai-2-27B-Uncensored-Heretic-v2
- Source repository
- OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-GGUF
- Base model
- prism-ml/Ternary-Bonsai-2-27B-gguf
- Publisher
- OS-Software
- 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
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, MLX
- First indexed
- 3 Oct 2026
- Last updated
- 14 Oct 2026
Ablation technique
How Ternary-Bonsai-2-27B-Uncensored-Heretic-v2 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 decensored version of Prism ML's Ternary-Bonsai-2-27B, with an OT-Ridge LoRA baked into the ternary weights. It succeeds Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF (v1).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-GGUF --local-dir ./ternary-bonsai-2-27b-uncensored-heretic-v2
llama-cli -m ./ternary-bonsai-2-27b-uncensored-heretic-v2/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-GGUF --trust-remote-codeDownloads and variants (2)
Every published repository of Ternary-Bonsai-2-27B-Uncensored-Heretic-v2, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| OS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-GGUFsource | GGUF | 61.6K |
| 3hs4n/Ternary-Bonsai-2-27B-Uncensored-Heretic-v2-mlx-2bit | MLX | 2.4K |
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-v2 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 prism-ml/Ternary-Bonsai-2-27B-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 prism-ml/Ternary-Bonsai-2-27B-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-v2 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with OS-Software, and does not independently verify publisher claims. See responsible use.