News for hackers. Stuff that matters.

A comment on Qwen3.7-Max: The Agent Frontier. Parent comment

Re:Qwen3.7-Max: The Agent Frontier by dzr0001 on Wednesday May 20, 2026 @03:42PM (#48213045)
My token throughput is much better using vLLM-mlx on my M2 ultra than llama.cpp. It might be worth a shot to give it a try.
[ Parent | on HN ]

There are no comments on this comment yet.