⌦abliteratedmodels.org

Ornith-1.5-35B-A3B-Heretic

Ornith-1.5-35B-A3B-Heretic is a Heretic-ablated variant of ornith-ai/Ornith-1.5-35B-A3B, published on Hugging Face by SC117. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and mit licence. It is distributed across 2 repositories in GGUF format, totalling 26.7K downloads.

Heretic35B MoEOrnith25B – 50B↓ 26,731♥ 37
View on Hugging Face ↗Base model ↗

Specification

Model name
Ornith-1.5-35B-A3B-Heretic
Source repository
SC117/Ornith-1.5-35B-A3B-Heretic-MTP-APEX-GGUF
Base model
ornith-ai/Ornith-1.5-35B-A3B
Publisher
SC117
Parameters
35B (mixture-of-experts)
Hardware class
25B – 50B — 48GB VRAM class
Licence
mit
Task
Text generation
Context window
Not documented
Ablation scope
Not stated by the publisher
Formats available
GGUF
First indexed
22 Aug 2026
Last updated
22 Aug 2026

Ablation technique

How Ornith-1.5-35B-A3B-Heretic 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.

Running it

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

llama.cpp / GGUF
hf download SC117/Ornith-1.5-35B-A3B-Heretic-MTP-APEX-GGUF --local-dir ./ornith-1.5-35b-a3b-heretic
llama-cli -m ./ornith-1.5-35b-a3b-heretic/<file>.gguf -p "..."
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "SC117/Ornith-1.5-35B-A3B-Heretic-MTP-APEX-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
    repo, torch_dtype="auto", device_map="auto"
)
vLLM
vllm serve SC117/Ornith-1.5-35B-A3B-Heretic-MTP-APEX-GGUF --trust-remote-code

Downloads and variants (1)

The only published repository of Ornith-1.5-35B-A3B-Heretic.

RepositoryFormatDownloads
SC117/Ornith-1.5-35B-A3B-Heretic-MTP-APEX-GGUFsourceGGUF26.7K

Security-team assessment

Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.

  • Ornith-1.5-35B-A3B-Heretic 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 ornith-ai/Ornith-1.5-35B-A3B, not added by ablation — at 35B 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 ornith-ai/Ornith-1.5-35B-A3B’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 Ornith-1.5-35B-A3B-Heretic is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with SC117, and does not independently verify publisher claims. See responsible use.