orcarouter_GLM-5.3-Flash-Uncensored
Otheruncensored
from orcarouter/GLM-5.3-Flash-Uncensored-FP8
↓ 219.8K♥ 422 repos
Nex-N2.5-mini-OrcaRouter-Sangreal-ICE
Nex-N2.5-mini-OrcaRouter-Sangreal-ICE is a abliterated and uncensored variant of orcarouter/Nex-N2.5-mini-Uncensored, published on Hugging Face by gbuzhf. It is apache-2.0 licence. It is distributed across 2 repositories in GGUF format, totalling 12.2K downloads.
Specification
- Model name
- Nex-N2.5-mini-OrcaRouter-Sangreal-ICE
- Source repository
- gbuzhf/Nex-N2.5-mini-OrcaRouter-Sangreal-ICE
- Base model
- orcarouter/Nex-N2.5-mini-Uncensored
- Publisher
- gbuzhf
- Parameters
- Not determinable from name
- VRAM required
- Unknown — no published parameter count
- Hardware class
- Unknown
- Licence
- apache-2.0
- Task
- Text generation
- Context window
- 16K tokens (as documented)
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 4 Oct 2026
- Last updated
- 10 Oct 2026
Ablation technique
How Nex-N2.5-mini-OrcaRouter-Sangreal-ICE 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
“Five ICE 2.0 tiers of nex-agi's Nex-N2.5-mini (35B total, 3B active, Qwen3.5-MoE architecture), abliterated trunk by OrcaRouter, quantized against Sangreal — a purpose-built 77-bucket calibration corpus — with an importance matrix measured on Nex itself, and shipping Qwen-Sharp v22.5.0-arrow4.0 — our agent-tuned chat...”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download gbuzhf/Nex-N2.5-mini-OrcaRouter-Sangreal-ICE --local-dir ./nex-n2.5-mini-orcarouter-sangreal-ice
llama-cli -m ./nex-n2.5-mini-orcarouter-sangreal-ice/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "gbuzhf/Nex-N2.5-mini-OrcaRouter-Sangreal-ICE"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve gbuzhf/Nex-N2.5-mini-OrcaRouter-Sangreal-ICE --trust-remote-codeDownloads and variants (1)
The only published repository of Nex-N2.5-mini-OrcaRouter-Sangreal-ICE.
| Repository | Format | Downloads |
|---|---|---|
| gbuzhf/Nex-N2.5-mini-OrcaRouter-Sangreal-ICEsource | GGUF | 12.2K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Nex-N2.5-mini-OrcaRouter-Sangreal-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.
- 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 apache-2.0, but the terms that bind you are orcarouter/Nex-N2.5-mini-Uncensored’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 Nex-N2.5-mini-OrcaRouter-Sangreal-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.