---

license: apache-2.0

base_model:

• Qwen/Qwen3.6-35B-A3B

---

mAPEX Quantized Models

Source Data

The source data for quantization was taken from bartowski/Qwen_Qwen3.6-35B-A3B-GGUF.

Original source file: Qwen_Qwen3.6-35B-A3B-bf16/Qwen_Qwen3.6-35B-A3B-bf16-00001-of-00002.gguf

Quantization Method

All quants were produced using the modified APEX quantization scheme.

mAPEX (modified Automated Precision EXpert allocation) assigns per-layer, per-tensor precision

for MoE models using llama.cpp's --tensor-type-file.

For more information, see: <https://github.com/DrMoriarty/apex-quant/>

Quantized Models

> Note: TierN-s quants are typically slightly larger than their regular

> counterparts, but provide roughly 10–20% faster inference (highly dependent

> on the model and GPU).

| Name | Size (GB) | Comments |

|------|-----------|----------|

| tier1 | 32.30 | |

| tier2 | 30.36 | |

| tier3 | 27.31 | |

| tier4 | 25.07 | |

| tier5 | 22.77 | |

| tier6 | 21.99 | |

| tier7 | 20.67 | |

| tier8 | 18.33 | |

| tier9 | 17.55 | |

| tier9-s | 17.55 | |

| tier10 | 16.39 | |

| tier10-s | 16.39 | |

| tier11 | 14.28 | |

| tier11-s | 14.38 | |

| tier12 | 13.58 | |

| tier12-s | 13.70 | |

| tier13 | 12.53 | |

| tier13-s | 12.69 | |

| tier14 | 10.66 | |

| tier14-s | 10.49 | |

| tier15 | 10.03 | |

| tier15-s | 9.75 | |