⌦abliteratedmodels.org

Ternary-Bonsai-2-27B-Heretic-Satellite

Ternary-Bonsai-2-27B-Heretic-Satellite is a Heretic-ablated open-weight language model, published on Hugging Face by HybridRMD. It is 27B parameters, 48GB VRAM class class and other licence. It is distributed across 2 repositories in GGUF format, totalling 8.3K downloads.

Heretic27BOther25B – 50B↓ 8,278
View on Hugging Face ↗

Specification

Model name
Ternary-Bonsai-2-27B-Heretic-Satellite
Source repository
HybridRMD/Ternary-Bonsai-2-27B-Heretic-Satellite
Base model
Not declared
Publisher
HybridRMD
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
other
Task
Text generation
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
27 Sept 2026
Last updated
30 Sept 2026

Ablation technique

How Ternary-Bonsai-2-27B-Heretic-Satellite 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 Qwen3.8-27B Bonsai 2 (Heretic) derivative carrying a small LoRA that turns a long working context into one structured compaction decision.”

Running it

Commands are templates — confirm the exact repository and quant file before use.

llama.cpp / GGUF
hf download HybridRMD/Ternary-Bonsai-2-27B-Heretic-Satellite --local-dir ./ternary-bonsai-2-27b-heretic-satellite
llama-cli -m ./ternary-bonsai-2-27b-heretic-satellite/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "HybridRMD/Ternary-Bonsai-2-27B-Heretic-Satellite"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve HybridRMD/Ternary-Bonsai-2-27B-Heretic-Satellite --trust-remote-code

Downloads and variants (1)

The only published repository of Ternary-Bonsai-2-27B-Heretic-Satellite.

RepositoryFormatDownloads
HybridRMD/Ternary-Bonsai-2-27B-Heretic-SatellitesourceGGUF8.3K

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-Heretic-Satellite 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.

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-Heretic-Satellite is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with HybridRMD, and does not independently verify publisher claims. See responsible use.