AI 导读
我们在 M5 Max MacBook Pro 上对 Qwen3.6-35B-A3B 进行了基准测试。 在十种提示词长度和十种解码上下文下，Lily 都比 MLX-LM 更快，平均 prefill 吞吐量高 1.23×，decode 吞吐量高 1.35×，同时输出质量基本保持不变。https://t.co/K7hWwYW7Ho
正文
We benchmark Qwen3.6-35B-A3B on an M5 Max MacBook Pro.
Across ten prompt lengths and ten decode contexts, Lily was faster than MLX-LM, averaging 1.23× higher prefill throughput and 1.35× higher decode throughput while keeping output quality effectively unchanged. https://t.co/K7hWwYW7Ho
来源：@perplexity_ai · x.com