Qwen3.6-35B-A3B-abliterated
35BQwen
from Qwen/Qwen3.6-35B-A3B
↓ 3.6M♥ 10545 repos
Qwen3.6-35B-A3B-Uncensored
Qwen3.6-35B-A3B-Uncensored is a abliterated and uncensored variant of Qwen/Qwen3.6-35B-A3B, published on Hugging Face by xCloudinfo. It is 35B total parameters (mixture-of-experts), 48GB VRAM class class and apache-2.0 licence. It is distributed across 6 repositories in NVFP4 and GGUF formats, totalling 27.7K downloads.
Specification
- Model name
- Qwen3.6-35B-A3B-Uncensored
- Source repository
- xCloudinfo/Qwen3.6-35B-A3B-Uncensored-GGUF
- Base model
- Qwen/Qwen3.6-35B-A3B
- Publisher
- xCloudinfo
- 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
- apache-2.0
- Task
- Text generation
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- NVFP4, GGUF
- First indexed
- 17 Apr 2026
- Last updated
- 26 Oct 2026
Ablation technique
How Qwen3.6-35B-A3B-Uncensored 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
“Based on Qwen/Qwen3.6-35B-A3B (qwen35moe hybrid linear-attention MoE + reasoning, 35B total / 3B active), this version reduces over-refusal through abliteration (refusal-direction orthogonalization). It is in GGUF quantized format and released by xCloudinfo (云碩科技).”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download xCloudinfo/Qwen3.6-35B-A3B-Uncensored-GGUF --local-dir ./qwen3.6-35b-a3b-uncensored
llama-cli -m ./qwen3.6-35b-a3b-uncensored/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "xCloudinfo/Qwen3.6-35B-A3B-Uncensored-GGUF"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve xCloudinfo/Qwen3.6-35B-A3B-Uncensored-GGUF --trust-remote-codeDownloads and variants (5)
Every published repository of Qwen3.6-35B-A3B-Uncensored, including quantised re-releases by other authors.
| Repository | Format | Downloads |
|---|---|---|
| xCloudinfo/Qwen3.6-35B-A3B-Uncensored-GGUFsource | GGUF | 20.3K |
| mecha-factory/Qwen3.6-35B-A3B-Uncensored-MTP-GGUF | GGUF | 5.6K |
| kyaky/Qwen3.6-35B-A3B-Uncensored-NVFP4 | NVFP4 | 1.4K |
| NeuralNet-Hub/Qwen3.6-35B-A3B-Uncensored-NVFP4 | NVFP4 | 486 |
| DuoNeural/Qwen3.6-35B-A3B-Uncensored-imatrix-GGUF | GGUF | 0 |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.6-35B-A3B-Uncensored 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/Qwen3.6-35B-A3B, 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 apache-2.0, but the terms that bind you are Qwen/Qwen3.6-35B-A3B’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 Qwen3.6-35B-A3B-Uncensored is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with xCloudinfo, and does not independently verify publisher claims. See responsible use.