Downloads · 30 days
45
4% of all-time downloads
IITheLordII/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4bit
Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4bit is a machine learning model from IITheLordII. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
MLX 4-bit conversion of DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking for native Apple Silicon inference.
Downloads · 30 days
45
4% of all-time downloads
All-time downloads
1.2K
Public
Parameters
27.4B
16.1 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
How the weights are stored.
U3226.9B · 98%
From the Hugging Face model README
MLX 4-bit conversion of DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking for native Apple Silicon inference.
This is an uncensored (Heretic2 abliterated) variant of Qwen 3.6 27B with fine-tuning for creative writing, reasoning, and coding — converted to MLX 4-bit quantization for fast, private, on-device inference on M-series Macs.
| Property | Value |
|---|---|
| Base model | Qwen/Qwen3.6-27B |
| Abliteration | Heretic2 by DavidAU (~95-99% refusal removal) |
| Format | MLX 4-bit (q-bits=4, group-size=64) |
| Parameters | ~27B |
| Vision | ✅ Preserved (multimodal) |
| Thinking mode | ✅ |
| Context window | 262K tokens |
| Languages | English, Chinese (140+) |
| Architecture | qwen3_5 |
mlx-vlm installedpip install mlx-vlm
from mlx_vlm import load, generate
model, processor = load("IITheLordII/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4bit")
output = generate(model, processor, prompt="Explain quantum computing simply.", max_tokens=512)
print(output)
from mlx_vlm import load, generate
model, processor = load("IITheLordII/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4bit")
output = generate(
model,
processor,
prompt="Describe what you see in this image.",
image="path/to/image.jpg",
max_tokens=256
)
print(output)
output = generate(
model,
processor,
prompt="<think>\nSolve step by step: what is the derivative of x^3 + 2x?\n</think>",
max_tokens=1024
)
Search IITheLordII/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking-mlx-4bit in the LM Studio model browser (MLX filter enabled).
| Context | TG (tok/s) |
|---|---|
| 1k | ~14-16 |
| 4k | ~14-16 |
Converted on Apple Silicon M4 Pro (24GB) using:
python3 -m mlx_vlm convert \
--hf-path DavidAU/Qwen3.6-27B-Heretic2-Uncensored-Finetune-Thinking \
--mlx-path ./qwen3.6-27b-heretic2-mlx-4bit \
-q --q-bits 4 --q-group-size 64
Note:
mlx-vlmis required (notmlx-lm) to preserve the vision tower.
Heretic2 is a multi-stage abliteration technique by DavidAU that removes refusal mechanisms while preserving model quality. Achieves ~95-99% refusal removal with minimal KL divergence from the original BF16 weights.
This model has its refusal mechanisms removed via abliteration. It may generate sensitive or controversial content. Use responsibly and in accordance with applicable laws and the Apache 2.0 license.