---

license: apache-2.0

base_model:

• Qwen/Qwen3.5-35B-A3B

---

mAPEX Quantized Models

Source Data

The source data for quantization was taken from unsloth/Qwen3.5-35B-A3B-GGUF.

Original source file: BF16/Qwen3.5-35B-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 |

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

| Qwen3.5-35B-A3B-Tier1.gguf | 31.46 | |

| Qwen3.5-35B-A3B-Tier2.gguf | 29.52 | |

| Qwen3.5-35B-A3B-Tier3.gguf | 26.48 | |

| Qwen3.5-35B-A3B-Tier4.gguf | 24.24 | |

| Qwen3.5-35B-A3B-Tier5.gguf | 21.94 | |

| Qwen3.5-35B-A3B-Tier6.gguf | 21.16 | |

| Qwen3.5-35B-A3B-Tier7.gguf | 20.03 | |

| Qwen3.5-35B-A3B-Tier8.gguf | 17.68 | |

| Qwen3.5-35B-A3B-Tier9.gguf | 16.90 | |

| Qwen3.5-35B-A3B-Tier9-s.gguf | 16.90 | |

| Qwen3.5-35B-A3B-Tier10.gguf | 15.82 | |

| Qwen3.5-35B-A3B-Tier10-s.gguf | 15.82 | |

| Qwen3.5-35B-A3B-Tier11.gguf | 13.71 | |

| Qwen3.5-35B-A3B-Tier11-s.gguf | 13.80 | |

| Qwen3.5-35B-A3B-Tier12.gguf | 13.00 | |

| Qwen3.5-35B-A3B-Tier12-s.gguf | 13.13 | |

| Qwen3.5-35B-A3B-Tier13.gguf | 12.03 | |

| Qwen3.5-35B-A3B-Tier13-s.gguf | 12.18 | |

| Qwen3.5-35B-A3B-Tier14.gguf | 10.15 | |

| Qwen3.5-35B-A3B-Tier14-s.gguf | 9.98 | |

| Qwen3.5-35B-A3B-Tier15.gguf | 9.53 | |

| Qwen3.5-35B-A3B-Tier15-s.gguf | 9.24 | |