Qwen3.5 9B Claude 4.6 HighIQ THINKING HERETIC UNCENSORED Fine tune via Unsloth of Qwen 3.5 9B dense model using Claude 4.6 large distill dataset on local hardware. This has VASTLY improved the thinking generation (and benchmarks) of this model replacing "Qwen 3.5" thinking with "Claude 4.6" thinking. Every attempt was made to ensure the training was "mild" and did not negatively affect the model's already incrediblely strong benchmarks. This is also a HERETIC model, trained post "Heretic'ing" this model does what you want, no questions asked. Fully uncensored. Vision (images) tested working with new training. BENCHMARKS: DE CENSORING: Performance KLD of less than 1 is excellent, zero is perfect. Metric This model Original model (Qwen/Qwen3.5 9B) : : : : : KL divergence 0.0793 0 (by definition) Refusals 6/100 100/100 NOTES: Suggest min q4ks (non imatrix) or IQ3S (imatrix). Tested with rep pen of 1 (off). Context: 256k (default). IMPORTANT: Other versions in testing. Information from Qwen's repo below. Video portions of the model were NOT TESTED. Qwen3.5 9B [!Note] This repository contains model weights and configuration files for the post trained model in the Hugging Face Transforme…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy