Qwen3.5-35B-A3B-oQ5

This model was quantized using oQ mixed-precision quantization.

Quantization details

  • Model type: qwen3_5_moe
  • Bits: 5
  • Group size: 128
  • Format: MLX safetensors
Downloads last month
228
Safetensors
Model size
6B params
Tensor type
U8
U32
BF16
F32
MLX
Hardware compatibility
Log In to add your hardware

5-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support