gemma-4-E4B-it-assistant-oQ8-fp16
This model was quantized using oQ (oMLX v0.3.9.dev1) mixed-precision quantization.
Quantization details
- Model type: gemma4_assistant
- Bits: 8
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 500
Model size
22.3M params
Tensor type
F16
路
U32 路
I64 路
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support