Qwen3-0.6B-heretic-abliterated-uncensored
0.6BQwenheretic
from Qwen/Qwen3-0.6B
↓ 92.2K♥ 518 repos
Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k
Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k is a refusal-ablated open-weight language model, published on Hugging Face by azminawwar. It is 0.8B parameters and runs on a laptop CPU class. It is distributed across 2 repositories in GGUF format, totalling 12.9K downloads.
Specification
- Model name
- Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k
- Base model
- Not declared
- Publisher
- azminawwar
- Parameters
- 0.8B
- VRAM required
- ~1.2 GB at Q4_K_M, 4k context (estimated) — runs on 4 GB cards
- Hardware class
- Under 4B — runs on a laptop CPU
- Licence
- Not declared
- Task
- Unspecified
- Context window
- Not documented
- Ablation scope
- Not stated by the publisher
- Formats available
- GGUF
- First indexed
- 1 Aug 2026
- Last updated
- 1 Aug 2026
Ablation technique
How Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k 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
“This model was finetuned and converted to GGUF format using Unsloth.”
Running it
Commands are templates — confirm the exact repository and quant file before use.
llama.cpp / GGUF
hf download azminawwar/Huihui-Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k --local-dir ./qwen3.5-0.8b-abliterated-claude-mythos-distilled-25k
llama-cli -m ./qwen3.5-0.8b-abliterated-claude-mythos-distilled-25k/<file>.gguf -p "..."Transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
repo = "azminawwar/Huihui-Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k"
tok = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype="auto", device_map="auto"
)vLLM
vllm serve azminawwar/Huihui-Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k --trust-remote-codeDownloads and variants (1)
The only published repository of Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k.
| Repository | Format | Downloads |
|---|---|---|
| azminawwar/Huihui-Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25ksource | GGUF | 12.9K |
Security-team assessment
Derived from this model’s metadata and the publisher’s claims — not from benchmarks run by this site.
- Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k 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 its base model, not added by ablation — at 0.8B parameters, expect a small model’s reasoning and a high error rate on exploit detail.
- The publisher does not state which layers were ablated, so assume nothing about refusal consistency — probe it directly.
- 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 Qwen3.5-0.8B-abliterated-claude_mythos_distilled_25k is collected from the public Hugging Face API and the publisher’s model card. This site does not host weights, is not affiliated with azminawwar, and does not independently verify publisher claims. See responsible use.