WizardLM-1.0-Uncensored-Llama2-13b
13BLlamauncensored
from QuixiAI/WizardLM-1.0-Uncensored-Llama2-13b
↓ 8.9K♥ 7510 repos
Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B
Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B is a abliterated and uncensored variant of DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B, published on Hugging Face by DavidAU. It is 8x3B total parameters (mixture-of-experts) and 24GB VRAM class class. It is distributed across 23 repositories in GGUF, Transformers, GGUF (imatrix) and MLX formats, totalling 43.6K downloads.
Specification
- Model name
- Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B
- Publisher
- DavidAU
- Parameters
- 8x3B (mixture-of-experts)
- Hardware class
- 10B – 25B — 24GB VRAM class
- Licence
- Not declared
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, Transformers, GGUF (imatrix), MLX
- First indexed
- 10 Dec 2024
- Last updated
- 29 Aug 2026
Ablation technique
How Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B 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
“This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF --local-dir ./llama-3.2-8x3b-moe-dark-champion-instruct-uncensored-abliterated-18.4b
llama-cli -m ./llama-3.2-8x3b-moe-dark-champion-instruct-uncensored-abliterated-18.4b/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B --trust-remote-codeDownloads and variants (22)
Every published repository of Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B, 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.
- Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B 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 DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B, not added by ablation — at 8x3B 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.
- No licence is declared on this repository, which is a compliance problem in itself. Resolve it against the base model’s terms before use.
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 Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with DavidAU, and does not independently verify publisher claims. See responsible use.