Qwen3.8 27B
on M6 32GB · Inco Splash
Summary
User reports Qwen3.8 27B running at 33-35 t/s on an M6 32GB Mac using the Inco Splash inference engine.
Other engines topped out at 9.6 t/s on the same machine.
The user is considering an M5 Pro for its 1.7x memory bandwidth and hopes Inco AI adds support for more models like Flash-Next.