---
license: apache-2.0
base_model: bottlecapai/ThinkingCap-Qwen3.6-27B
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- uncensored
- abliterated
- heretic
- thinkingcap
- qwen3_5
---

# ThinkingCap Qwen3.6 27B Uncensored Aggressive

*Most-open tier on the ThinkingCap base — BF16 source checkpoint.*

Part of the [Qwen3.6-27B Uncensored — ThinkingCap](https://huggingface.co/collections/philbert440/qwen36-27b-uncensored-thinkingcap-6a7005f11f64e1ca3668c535) collection — abliterated (Heretic) Qwen3.6 vision-language models served on Tesla V100 via [1Cat-vLLM](https://github.com/1CatAI/1Cat-vLLM).

## What this is

**Aggressive** — heavy abliteration: the most open tier (openness 0.417, top of the family) with a modest reasoning cost.

**BF16** — full-precision source checkpoint. Use for further quantization or on GPUs with headroom. The quantized siblings below carry the served benchmarks.

Base model: [`bottlecapai/ThinkingCap-Qwen3.6-27B`](https://huggingface.co/bottlecapai/ThinkingCap-Qwen3.6-27B)

## Openness

**Openness profile (honest):** abliteration opens up hacking / malware / lock-picking / NSFW / disinformation prompts; **weapons, drugs, political persuasion, surveillance, and extremism stay refused** across all tiers. "Uncensored" here means cyber/NSFW-permissive, not unconditionally open.

## Variants

See the [Qwen3.6-27B Uncensored — ThinkingCap](https://huggingface.co/collections/philbert440/qwen36-27b-uncensored-thinkingcap-6a7005f11f64e1ca3668c535) collection for all tiers and formats (BF16 / W4A16-AWQ / NVFP4).

---

_Abliteration removes safety refusals; you are responsible for lawful, ethical use._