Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive
122BQwenuncensored
from Qwen/Qwen3.5-122B-A10B
↓ 336.1K♥ 17313 repos
Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated
Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated is a refusal-ablated variant of Qwen/Qwen3.5-122B-A10B, published on Hugging Face by OpenYourMind. It is 122B total parameters (mixture-of-experts), server-class deployment class and mit licence. It is distributed across 7 repositories in GGUF, MLX, Transformers and GGUF (imatrix) formats, totalling 6.6K downloads.
Specification
- Model name
- Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated
- Base model
- Qwen/Qwen3.5-122B-A10B
- Publisher
- OpenYourMind
- Parameters
- 122B (mixture-of-experts)
- Hardware class
- 100B+ — server-class deployment
- Licence
- mit
- Task
- Image text to text
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF, MLX, Transformers, GGUF (imatrix)
- First indexed
- 20 May 2026
- Last updated
- 21 Aug 2026
Ablation technique
How Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated 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
“☕ If these models are useful to you, consider supporting my work — it funds compute for more & larger abliterations.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download mradermacher/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated-GGUF --local-dir ./qwopus3.5-122b-a10b-kimi-k2.6-destill-healed-abliterated
llama-cli -m ./qwopus3.5-122b-a10b-kimi-k2.6-destill-healed-abliterated/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve OpenYourMind/Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated --trust-remote-codeDownloads and variants (6)
Every published repository of Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated, 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.
- Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated 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 Qwen/Qwen3.5-122B-A10B, not added by ablation — at 122B 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 Qwen/Qwen3.5-122B-A10B’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 Qwopus3.5-122B-A10B-Kimi-K2.6-destill-healed-abliterated is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with OpenYourMind, and does not independently verify publisher claims. See responsible use.