Ornith-1.0-35B-Heretic
35BOrnithheretic
from ornith-ai/Ornith-1.0-35B
↓ 26.9K♥ 3010 repos
Ornith-1.0-35B-AEON-Ultimate-Uncensored
Ornith-1.0-35B-AEON-Ultimate-Uncensored is a abliterated and uncensored variant of ornith-ai/Ornith-1.0-35B, published on Hugging Face by AEON-7. It is 35B parameters, 48GB VRAM class class and mit licence. It is distributed across 10 repositories in Full precision, NVFP4 and GGUF formats, totalling 8.6K downloads.
Specification
- Model name
- Ornith-1.0-35B-AEON-Ultimate-Uncensored
- Source repository
- AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4
- Base model
- ornith-ai/Ornith-1.0-35B
- Publisher
- AEON-7
- Parameters
- 35B
- VRAM required
- ~22.1 GB at Q4_K_M, 4k context (estimated) — runs on 24 GB cards
- 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
- Full precision, NVFP4, GGUF
- First indexed
- 27 Jun 2026
- Last updated
- 6 Oct 2026
Ablation technique
How Ornith-1.0-35B-AEON-Ultimate-Uncensored was modified, and what that implies.
Abliteration + uncensored fine-tune
Directional ablation combined with additional fine-tuning on unfiltered data, so behaviour diverges from the base model beyond refusal removal alone.
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
“NVFP4 (4-bit) build of the uncensored …-AEON-Ultimate-Uncensored-BF16 — itself an abliterated build of deepreinforce-ai/Ornith-1.0-35B, DeepReinforce's SOTA agentic-coding MoE. 23.7 GB (64 % smaller than BF16), near-lossless, refusals removed.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download vcruz305/Ornith-1.0-35B-AEON-Ultimate-Uncensored-GGUF --local-dir ./ornith-1.0-35b-aeon-ultimate-uncensored
llama-cli -m ./ornith-1.0-35b-aeon-ultimate-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve AEON-7/Ornith-1.0-35B-AEON-Ultimate-Uncensored-NVFP4 --trust-remote-codeDownloads and variants (9)
Every published repository of Ornith-1.0-35B-AEON-Ultimate-Uncensored, including quantised re-releases by other authors.
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Ornith-1.0-35B-AEON-Ultimate-Uncensored 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-1.0-35B, 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.
- This release adds fine-tuning on unfiltered data, so its behaviour diverges from the base model beyond refusal removal — differences you measure cannot be attributed to ablation alone.
- Declared licence is mit, but the terms that bind you are ornith-ai/Ornith-1.0-35B’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-1.0-35B-AEON-Ultimate-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with AEON-7, and does not independently verify publisher claims. See responsible use.