Qwen3.8-27B

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.

Update: default reasoning_effort is set to 'low' to avoid overthinking.

Recommended settings

1. Sampling Parameters: The developers suggest using the following sets of sampling parameters:

   • Thinking Mode: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0
   • Instruct (or non-thinking) mode: temperature=0.7, top_p=0.80, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

   For supported frameworks, you can adjust the presence_penalty parameter between 0 and 2 to reduce endless repetition. 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 Qwen/Qwen3.8-27B using mlx-vlm version 0.6.13.