Tiny Random Qwen3 DFlash b16

Tiny random DFlash draft model compatible with optimum-intel-internal-testing/tiny-random-qwen3.

  • Source remote-code template: z-lab/Qwen3-4B-DFlash-b16
  • Target hidden size: 32
  • Target hidden layers: 2
  • DFlash block size: 16
  • DFlash target layer ids: [0, 1]
Downloads last month
35
Safetensors
Model size
30.9k params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support