TheCluster/Huihui-Qwen3.6-27B-Abliterated-MLX-mixed-9.4bit

<div align="center"><img width="400px" src="https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.6/logo.png"></div> <div style="text-align:center; margin-bottom:12pt">If you like my work, you can <a href="https://donatr.ee/thecluster/">support me</a><br/></div>

Qwen3.6-27B Abliterated (by huihui.ai)

This is another uncensored version of Qwen/Qwen3.6-27B, made by huihui.ai.

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.

Alternative version (from other source): `TheCluster/Qwen3.6-27B-Heretic-MLX-mixed-9.4bit`

Recommended settings

1. 1.Sampling Parameters:
2. 2.The developers suggest using the following sets of sampling parameters depending on the mode and task type:
3. 3.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
4. 4.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
5. 5.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
6. 6.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
7. 7.For supported frameworks, you can adjust the presence_penalty parameter 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 `huihui-ai/Huihui-Qwen3.6-27B-abliterated` using mlx-vlm version 0.4.4.