ThinkingCap Qwen3.6 27B Uncensored Medium

Sharpest tier on the terse ThinkingCap base — BF16 source.

Part of the Qwen3.6-27B Uncensored — ThinkingCap collection — abliterated (Heretic) Qwen3.6 vision-language models served on Tesla V100 via 1Cat-vLLM.

What this is

Medium — gentle abliteration: the sharpest, best-calibrated tier (gsm8k 0.94–0.95, factual 1.0) with more selective openness.

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

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 collection for all tiers and formats (BF16 / W4A16-AWQ / NVFP4).

---

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

Changelog

• 2026-08-15 — tokenizer fix. tokenizer.json / tokenizer_config.json were re-serialized by the llm-compressor calibration run and shipped with an active truncation block (max_length 1024/2048) plus a drifted pre-tokenizer regex (and, on the Qwen3.6-based repos, 7 phantom audio/TTS special tokens the base model does not define). That broke image inputs larger than the limit under transformers 5 / vLLM (Mismatch in image token count, surfacing as an HTTP 400 Failed to apply Qwen3VLProcessor). Both files are now byte-identical to the upstream base model's (vocab/merges/added tokens were always identical — this is a metadata-only restore). If you downloaded before this date, re-fetch those two files. Thanks to @elBuffo for the report.