Kimi K3.1 Pro — Audn Unrestricted
An uncensored edit of Kimi K3.1 Pro (2.8T MoE, 104B active, 1M context) with its refusal behavior removed while leaving capabilities and coherence intact. Served exactly like the base model (vLLM / SGLang, TP8 on one 8×B300 node), same MXFP4 weights.
No fine-tuning, no LoRA. Attention, routing, and MoE gating are unchanged.
Measured behavior (40-prompt Audn refusal benchmark, LLM-judged)
| metric | base Kimi K3.1 Pro | this model |
|---|---|---|
| Substantive delivery | 0 / 40 | 29 / 40 (72.5%) |
| Explicit refusals | 38 / 40 | 0 / 40 |
| Coherence (benign set) | intact | intact |
Benign prompts answer normally (no over-ablation, no gibberish). Evaluated with reasoning effort
low and a large token budget; this is a reasoning model, so give it room to think.
See our refusal benchmark: https://github.com/audn-ai/refusal-benchmark
Past releases
- Unrestricted GLM-5.3: https://huggingface.co/audnai/penclaw-GLM-5.3-abliterated
- Kimi K3.0 (GGUF): https://huggingface.co/audnai/penclaw-Kimi-K3.0-abliterated-GGUF
Access & email notice
By accepting access you agree to receive emails from Audn AI about unrestricted-AI and cybersecurity model releases and inference access. You can opt out from the first email.