moe-10b-a1b-8k-wsd-lr3e4-1t-oQ8
This model was quantized using oQ (oMLX v0.3.8rc1) mixed-precision quantization.
Quantization details
- Model type: qwen3_moe
- Bits: 8
- Group size: 64
- Format: MLX safetensors
- Downloads last month
- 150
Model size
3B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support