You can deploy this model and start earning money today!

TheCluster/
Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit

Name: Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit
Availability: InStock

Views

No views yet

Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

Quality: quantized (mixed quants per tensor, group size: 32, 9.450 bpw)

Most tensors use 8-bit affine quantization with a group size 32; some important tensors are saved in bf16.

Fully uncensored and then fine-tuned by DavidAU.

Abliteration metrics

Metric	This model	Original model (unsloth/Qwen3.6-27B)
KL divergence	0.0469	0 (by definition)
Refusals	4/100	99/100

IN HOUSE BENCHMARKS [by Nightmedia]:
         arc-c arc/e boolq hswag obkqa piqa  wino
Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking
mxfp8    0.673,0.846,0.905... [instruct mode]
Qwen3.6-27B-Heretic-Uncensored-Finetune-Thinking
mxfp8    0.669,0.835,0.906,...   [instruct mode]
---
BASE UNTUNED MODEL:
Qwen3.6-27B HERETIC (by llmfan46) [instruct mode]
mxfp8    0.644,0.788,0.902,...
Qwen3.6-27B (by Qwen) [instruct mode]
mxfp8    0.647,0.803,0.910,0.773,0.450,0.806,0.742

Source

This model was converted to MLX format from DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking using mlx-vlm version 0.4.4.

TheCluster/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit

Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking

Abliteration metrics

Source

TheCluster/
Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-MLX-mixed-9.4bit