Qwen3.6-35B-A3B on 4× Intel Arc Pro B70: Achieving 200 tok/s
The Qwen3.6-35B-A3B model offers four optimized configurations with 4 Intel Arc Pro B70 GPUs, balancing performance and flexibility.
The Qwen3.6-35B-A3B model introduces four optimized configurations using four Intel Arc Pro B70 GPUs. These setups cater to various needs, including low-latency single-stream performance, high concurrency, and full precision. Users can select their preferred configuration from a single Docker image for rapid deployment and benchmarking.