license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3.5-27B/blob/main/LICENSE base_model:
- DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking base_model_relation: quantized library_name: mlx tags:
- uncensored
- abliterated
- heretic
- nsfw
- unsloth
- deckard
- fine tune
- all use cases
- coder
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- fiction writing
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prosing
- vivid writing
- fiction
- roleplaying
- bfloat16
- all use cases pipeline_tag: image-text-to-text language:
- en
- zh
WARNING: This model has character and intelligence. Uncensored, Unfiltered and boldly confident. Not even remotely "SFW", if you ask it for NSFW content. And it is wickedly smart too.
Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
Quality: original bfloat16
40 billion parameters (dense, not moe) expanded from Qwen3.5 27B, then trained on Claude 4.6 Opus High Reasoning dataset via Unsloth on local hardware.
96 layers, 1275 Tensors. (50% more than base model of 27B)
Features variable length reasoning ; less complex = shorter, longer for more complex.
Model performance has increased dramatically. And it has character too.
256K context.
Fully uncensored first (via Heretic), then trained (via Unsloth) on "Deckard/PDK" internal datasets (5) (character, intelligence, depth, observation, and ah... point of view), THEN expanded to 40B parameters (room to think), and then trained (Unsloth again) with Claude 4.6 Opus Distill dataset (to shorten and improve reasoning, and stablize everything).
SETTINGS:
- min 8k to 16k context window.
- for creative rep pen of 1.05 to 1.1 WITH LOWER QUANTS.
- suggest temp .7 / rep pen 1 (off) for general usage.
- output generation can exceed 100k tokens.
- For toolcalls -> suggest 6bit min quants (as per Qwen guidence)
INSTRUCT MODE: The model's default mode however is "THINKING" ; this can be changed by editing the following line in the jinja template:
{# Set Instruct mode here #}
to
{%- set enable_thinking = false %}
Source
This model was converted to MLX format from DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking using mlx-vlm version 0.4.