georgeis55/Ornith-1.0-35B-refusal-ablated-MLX-oQ8
0138
Ornith-1.0-35B-refusal-ablated-MLX-oQ8
This model was quantized using oQ (oMLX v0.4.5.dev1) mixed-precision quantization.
Quantization details
- Model type: qwen35moe
- Bits: 8
- Group size: 64
- Format: MLX safetensors
