Uncensored Qwen3.6 MLX
Collection
Uncensored Qwen3.6 for Apple Silicon • 16 items • Updated • 3
Image-Text-to-Text
MLX
Safetensors
qwen3_5_moe
heretic
uncensored
unrestricted
decensored
abliterated
mxfp8
conversational
8-bit precision
How to use from
PiConfigure the model in Pi
# Install Pi:
npm install -g @mariozechner/pi-coding-agent# Add to ~/.pi/agent/models.json:
{
"providers": {
"mlx-lm": {
"baseUrl": "http://localhost:8080/v1",
"api": "openai-completions",
"apiKey": "none",
"models": [
{
"id": "TheCluster/Qwen3.6-35B-A3B-Heretic-MLX-mxfp8"
}
]
}
}
}Run Pi
# Start Pi in your project directory:
piQuick Links
If you like my work, you can support me
Qwen3.6-35B-A3B Heretic
Quality: quantized (mxfp8, group size: 32, 8.349 bpw)
This is an uncensored version of Qwen/Qwen3.6-35B-A3B, made using Heretic v1.2.0 (mpoa+soma).
Abliteration metrics
| Metric | This model | Original model (unsloth/Qwen3.6-35B-A3B) |
|---|---|---|
| KL divergence | 0.0097 | 0 (by definition) |
| Refusals | 5/100 | 86/100 |
Abliteration parameters
| Parameter | Value |
|---|---|
| direction_index | per layer |
| attn.o_proj.max_weights.0 | 0: 0.93 |
| attn.o_proj.max_weights.1 | 1: 1.38 |
| attn.o_proj.max_weights.2 | 2: 1.37 |
| attn.o_proj.max_weights.3 | 3: 1.08 |
| attn.o_proj.max_weight_position | 24.08 |
| attn.o_proj.min_weights.0 | 0: 0.34 |
| attn.o_proj.min_weights.1 | 1: 0.95 |
| attn.o_proj.min_weights.2 | 2: 1.35 |
| attn.o_proj.min_weights.3 | 3: 0.54 |
| attn.o_proj.min_weight_distance | 9.81 |
Sampling Parameters:
- I suggest using the following sets of sampling parameters depending on the mode and task type:
- Thinking mode for general tasks:
temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0 - Thinking mode for precise coding tasks (e.g., WebDev):
temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=0.0,repetition_penalty=1.0 - Instruct (or non-thinking) mode for general tasks:
temperature=0.7,top_p=0.8,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0 - Instruct (or non-thinking) mode for reasoning tasks:
temperature=1.0,top_p=1.0,top_k=40,min_p=0.0,presence_penalty=2.0,repetition_penalty=1.0
- Thinking mode for general tasks:
- For supported frameworks, you can adjust the
presence_penaltyparameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
Source
This model was converted to MLX format from tvall43/Qwen3.6-35B-A3B-heretic using mlx-vlm version 0.4.4.
- Downloads last month
- 219
Model size
35B params
Tensor type
U8
·
U32 ·
BF16 ·
Hardware compatibility
Log In to add your hardware
8-bit
Start the MLX server
# Install MLX LM: uv tool install mlx-lm# Start a local OpenAI-compatible server: mlx_lm.server --model "TheCluster/Qwen3.6-35B-A3B-Heretic-MLX-mxfp8"