granite-4.1-3b-oQ5-fp16
This model was quantized using oQ (oMLX v0.3.8rc1korokke) mixed-precision quantization.
Quantization details
- Model type: granite
- Bits: 5
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 205
Model size
0.7B params
Tensor type
F16
·
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
Model tree for RepublicOfKorokke/granite-4.1-3b-oQ5-fp16
Base model
ibm-granite/granite-4.1-3b