Accelerating Qwen3.6 on Intel® Core™ Ultra Series 3 with DFlash

Back to Articles

TL;DR

Qwen3.6-35B-A3B is a highly efficient Mixture-of-Experts (MoE) model that brings strong coding, reasoning, and agentic capabilities to the AI PC, making it a stepping stone toward local AI.

MoE models are more challenging to accelerate with Speculative Decoding (SD): verifying several drafted tokens can pull in many more experts, dramatically inflating the effective active parameter count.

Running Qwen3.6-35B-A3B with DFlash SD and OpenVINO™ on an Intel® Panther Lake laptop, we achieve an average speedup of 2.2x on HumanEval (90 t/s), 1.3x on MT-Bench and 1.6x on GSM8K.