AI is happening. The future is updating.Qwen3-14B-Abliterated-GGUF
GGUF quants of the RootMonsteR abliterated Qwen3-14B — for llama.cpp , Ollama, LM Studio, Jan, and KoboldCpp. These are quantized **GGUF** builds of `RootMonsteR/Qwen3-14B-Abliterated` — a Heretic v1.3.0 abliteration of `Qwen/Qwen3-14B` that removes **~90% of refusals** (10/100 vs 99/100) at an exceptionally low **KL divergence of 0.0333**, tuned for autonomous agents, tool-use, and authorized security work. Both run comfortably on CPU with 16 GB+ system RAM (slower). For full-precision **bf16** (servers / vLLM), use the source repo.
GGUF quants of the RootMonsteR abliterated Qwen3-14B — for llama.cpp , Ollama, LM Studio, Jan, and KoboldCpp. These are quantized **GGUF** builds of `RootMonsteR/Qwen3-14B-Abliterated` — a Heretic v1.3.0 abliteration of `Qwen/Qwen3-14B` that removes **~90% of refusals** (10/100 vs 99/100) at an exceptionally low **KL divergence of 0.0333**, tuned for autonomous agents, tool-use, and authorized security work. Both run comfortably on CPU with 16 GB+ system RAM (slower). For full-precision **bf16** (servers / vLLM), use the source repo.