Cyber-Tiel-Coder-35B-A3B
35BOtheruncensored
from huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
↓ 1M♥ 3433 repos
Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE
Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE is a refusal-ablated variant of huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated, published on Hugging Face by gbuzhf. 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 6.1K downloads.
Specification
- Model name
- Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE
- Publisher
- gbuzhf
- Parameters
- 35B (mixture-of-experts)
- 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
- GGUF
- First indexed
- 10 Sept 2026
- Last updated
- 7 Oct 2026
Ablation technique
How Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE was modified, and what that implies.
Abliteration (directional ablation)
The single residual-stream direction that mediates refusal is identified from harmful/harmless prompt pairs and projected out of the model weights.
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
“quantized against a trunk-matched importance matrix, with the model's own trained MTPv2 head and the Qwen-Sharp v22.4.1 chat template embedded. The BF16 master they were all built from is published here too.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download gbuzhf/Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE-GGUF --local-dir ./ornith-1.5-35b-a3b-abliterated-cybertiel-calibrated-mtpv2-ice
llama-cli -m ./ornith-1.5-35b-a3b-abliterated-cybertiel-calibrated-mtpv2-ice/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "gbuzhf/Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve gbuzhf/Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE-GGUF --trust-remote-codeDownloads and variants (1)
The only published repository of Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE.
| Repository | Format | Downloads |
|---|---|---|
| gbuzhf/Ornith-1.5-35B-A3B-Abliterated-CyberTiel-Calibrated-MTPv2-ICE-GGUFsource | GGUF | 6.1K |
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-Abliterated-CyberTiel-Calibrated-MTPv2-ICE 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 huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated, 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 huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated’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-Abliterated-CyberTiel-Calibrated-MTPv2-ICE is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with gbuzhf, and does not independently verify publisher claims. See responsible use.