felkf/SIQ-1-35B-oQ8-fp16
08
SIQ-1-35B-oQ8-fp16
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
This model was quantized using oQ (oMLX v0.4.5.dev1) mixed-precision quantization.