GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
philbert440
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
philbert440
Model Tree
bottlecapai/ThinkingCap-Qwen3.6-27B
Input Modalities
Output Modalities
Supported Functionality
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 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.
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.
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.