Qwen3.8 27B
on M5 Max · oMLX
Use cases
coding
Summary
User reports Qwen3.8 27B at about 28 tokens a second on an M5 Max Mac Studio, run with oMLX and Splash.
The user's complaint is verbosity rather than throughput: the 27B thinks for 10 minutes and generates far more tokens than the Qwen 35B MoE, taking 20 minutes on a task the 35B finishes in 2 minutes, across all harnesses tried.
The user asks whether others see the same behavior.