EXL3 quantization of Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1, 8 bits per weight, including output layers.
HumanEval (argmax)
| Model | Q4 | Q6 | Q8 | FP16 |
|---|---|---|---|---|
| Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-exl3-8bpw-h8 | 75.6 | 76.8 | 79.3 | 80.5 |
| DeepSeek-R1-0528-Qwen3-8B-exl3-8bpw | 79.9 | 77.4 | 78.7 | 79.3 |
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for isogen/Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-exl3-8bpw-h8
Base model
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B