Ornith-1.5-35B-A3B-Huihui-Sangreal-MTP-ICE
35BOrnithuncensored
from huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated
↓ 23.7K♥ 6
Cyber-Tiel-Coder-35B-A3B
Cyber-Tiel-Coder-35B-A3B is a abliterated and uncensored variant of huihui-ai/Huihui-Ornith-1.5-35B-A3B-abliterated, published on Hugging Face by peculiar-ragdoll. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and mit licence. It is distributed across 4 repositories in GGUF format, totalling 1M downloads.
Specification
- Model name
- Cyber-Tiel-Coder-35B-A3B
- Source repository
- peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP
- Publisher
- peculiar-ragdoll
- 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
- Image text to text
- Context window
- 262K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 31 Aug 2026
- Last updated
- 26 Oct 2026
Ablation technique
How Cyber-Tiel-Coder-35B-A3B 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
“CyberTiel outcodes every other 35B-A3B at Q4 quantization (and spring-of-2026 frontier models), while engaging with offensive security work without hesitation or refusal. As a sweet spot between speed and ability, CyberTiel delivers agentic coding solves about 3-4x faster than 3.8-27B dense. This is the first time the...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP --local-dir ./cyber-tiel-coder-35b-a3b
llama-cli -m ./cyber-tiel-coder-35b-a3b/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTP --trust-remote-codeDownloads and variants (3)
Every published repository of Cyber-Tiel-Coder-35B-A3B, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTPsource | GGUF | 962.2K |
| peculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF | GGUF | 79.7K |
| ArkhAngelLifeJiggy/Cyber-Tiel-Coder-35B-A3B-GGUF | GGUF | 618 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Cyber-Tiel-Coder-35B-A3B 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.
- 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 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 Cyber-Tiel-Coder-35B-A3B is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with peculiar-ragdoll, and does not independently verify publisher claims. See responsible use.