Qwen3.5 9B Star Trek TNG DS9 Heretic Uncensored Thinking MAX NEOCODE GGUF EU AI Act Compliance Profile

Fine tune via Unsloth of Qwen 3.5 9B dense model using Star Trek TNG/DS9 in house datasets.

This was about giving the model specific "trek" training and knowledge as well as making the model itself a "trekie" too.

Training has SLIGHTLY altered thinking, and trimmed it down a bit / made it more "sure of itself" (fewer tokens/really long gens).

Also changes to prose (style, word choice, dialog) have been noted.

Training also raised all benchmarks too.

Every attempt was made to ensure the training was "mild" and did not negatively affect the model's already incredibly strong benchmarks.

This is also a HERETIC model, trained post "Heretic'ing" -> this model does what you want, no questions asked.

Fully uncensored.

FIVE Example generations at the bottom of the page.

Vision (images) tested -> working with new training.

GGUF POWER UPS:

• DI-MATRIX (duel imatrix) of NEO and NEO-CODE imatrix datasets (by DavidAU).
• All Unsloth tensor enhancements (but at BF16).
• BF16 output tensor to improve both thinking and output.
• Custom Jinja template (by DavidAU/Nightmedia) to address some issues with the Qwen 3.5 model series (stablize and reduce overthinking).

A radically stronger, more potent GGUF for all use cases.

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

Your obligations as a Qwen3.5 9B Star Trek TNG DS9 Heretic Uncensored Thinking MAX NEOCODE GGUF deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Base Model