Ornith-1.0-35B-AEON-Ultimate-Uncensored
35BOrnithuncensored
from deepreinforce-ai/Ornith-1.0-35B
↓ 438.2K♥ 5910 repos
Ornith-1.5-35B-A3B-Heretic-GB10
Ornith-1.5-35B-A3B-Heretic-GB10 is a Heretic-ablated variant of OS-Software/Ornith-1.5-35B-A3B-heretic-ja, published on Hugging Face by spele1100. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and mit licence. It is distributed across 2 repositories in NVFP4 format, totalling 5.9K downloads.
Specification
- Model name
- Ornith-1.5-35B-A3B-Heretic-GB10
- Source repository
- spele1100/Ornith-1.5-35B-A3B-Heretic-GB10-NVFP4
- Publisher
- spele1100
- Parameters
- 35B (mixture-of-experts)
- Hardware class
- 25B – 50B — 48GB VRAM class
- Licence
- mit
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- NVFP4
- First indexed
- 23 Aug 2026
- Last updated
- 23 Aug 2026
Ablation technique
How Ornith-1.5-35B-A3B-Heretic-GB10 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 mixed-precision NVFP4/FP8 conversion of the Ornith-1.5-35B-A3B Heretic-JA model, optimized for NVIDIA GB10 (DGX Spark / Spark Mini, SM121) — a GPU without native FP4 compute. Decode on GB10 is memory-bandwidth-bound, so 4-bit expert weights cut bytes moved per token by ~3× and run through fused...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "spele1100/Ornith-1.5-35B-A3B-Heretic-GB10-NVFP4"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve spele1100/Ornith-1.5-35B-A3B-Heretic-GB10-NVFP4 --trust-remote-codeDownloads and variants (1)
The only published repository of Ornith-1.5-35B-A3B-Heretic-GB10.
| Repository | Format | Downloads |
|---|---|---|
| spele1100/Ornith-1.5-35B-A3B-Heretic-GB10-NVFP4source | NVFP4 | 5.9K |
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-GB10 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/Ornith-1.5-35B-A3B-heretic-ja, 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 OS-Software/Ornith-1.5-35B-A3B-heretic-ja’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-GB10 is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with spele1100, and does not independently verify publisher claims. See responsible use.