This quantization was uploaded on 2026-03-31 and replaces a previous version. If you downloaded this model before this date, please re-download for the updated weights.

Qwen3.5-35B-A3B-oQ4e

This model was quantized using oQ (oMLX v0.3.1) mixed-precision quantization.

Quantization details

  • Model type: qwen3_5_moe
  • Bits: 4
  • Group size: 64
  • Format: MLX safetensors
Downloads last month
2,312
Safetensors
Model size
6B params
Tensor type
BF16
U32
F32
MLX
Hardware compatibility
Log In to add your hardware

4-bit

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