Phi-4-reasoning-plus-oQ5e
This model was quantized using oQ (oMLX v0.3.8) mixed-precision quantization.
Quantization details
- Model type: phi3
- Bits: 5
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 173
Model size
3B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
5-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support