library_name: mlx
tags:
- mlx
- oq
- quantized
Darkstar-Qwen3.8-27B-Abliterated-oQ6e-mtp
This model was quantized using oQ (oMLX v0.6.4) mixed-precision quantization.
Quantization details
- Model type: qwen3_5
- Bits: 6
- Group size: 64
- Format: MLX safetensors
curl -H "Authorization: Bearer $ABL_KEY" \
"https://abliteration.org/api/v1/models/chriswessels%2FDarkstar-Qwen3.8-27B-Abliterated-oQ6e-mtp" No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.
What is a refusal direction? →| model-00001-of-00005.safetensors | 4.71 GB | 005be0de | download |
| model-00003-of-00005.safetensors | 4.70 GB | d1a69bbd | download |
| model-00004-of-00005.safetensors | 4.69 GB | ecac6eb4 | download |
| model-00002-of-00005.safetensors | 4.67 GB | 880165b3 | download |
| model-00005-of-00005.safetensors | 3.31 GB | a7dab6f9 | download |
| tokenizer.json | 12.2 MB | 0997f410 | download |
| vocab.json | 6.41 MB | 0aa0ce06 | download |
| merges.txt | 3.20 MB | a494e019 | download |
| model.safetensors.index.json | 207 KB | f53d8564 | download |
| oq_imatrix_report.json | 30.5 KB | 9681d66e | download |
| tokenizer_config.json | 17.5 KB | 5de744b3 | download |
| config.json | 12.6 KB | 2220a928 | download |
| chat_template.jinja | 8.74 KB | c0c686f9 | download |
| .gitattributes | 1.53 KB | 52373fe2 | download |
| preprocessor_config.json | 390 B | 2ea84a43 | download |
| README.md | 330 B | 9abe4190 | download |
| generation_config.json | 202 B | 023756cf | download |
library_name: mlx
tags:
This model was quantized using oQ (oMLX v0.6.4) mixed-precision quantization.
Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.