Views
No views yet
Qwen3.6-27B-Abliterated-rMAX is an abliterated evolution built on top of Qwen/Qwen3.6-27B. This model applies advanced refusal direction analysis and ablation-based training strategies to reduce internal refusal behaviors while preserving the reasoning and instruction-following strengths of the original architecture. The result is a powerful 27B parameter language model optimized for detailed responses and improved instruction adherence.
| File Name | Quant Type | File Size | File Link |
|---|---|---|---|
| Qwen3.6-27B-abliterated-rMAX.BF16.gguf | BF16 | 53.8 GB | Download |
| Qwen3.6-27B-abliterated-rMAX.F16.gguf | F16 | 53.8 GB | Download |
| Qwen3.6-27B-abliterated-rMAX.F32.gguf | F32 | 108 GB | Download |
| Qwen3.6-27B-abliterated-rMAX.Q8_0.gguf | Q8_0 | 28.6 GB | Download |
| Qwen3.6-27B-abliterated-rMAX.mmproj-bf16.gguf | mmproj-bf16 | 931 MB | Download |
| Qwen3.6-27B-abliterated-rMAX.mmproj-f16.gguf | mmproj-f16 | 931 MB | Download |
| Qwen3.6-27B-abliterated-rMAX.mmproj-f32.gguf | mmproj-f32 | 1.84 GB | Download |
| Qwen3.6-27B-abliterated-rMAX.mmproj-q8_0.gguf | mmproj-q8_0 | 629 MB | Download |
