Inco Splash Open-Source Engine Runs Qwen3.8-27B at 144 tok/s on M5 Max

Inco has released Splash, an open-source inference engine optimized for Apple Silicon with a built-in DFlash 2 draft model. It runs Qwen3.8-27B at 144 tok/s on the M5 Max MacBook Pro with just two commands.

2026-09-19 ~ 2026-09-19 · 2 related posts

• Inco Splash open-source engine hits 144 tok/s on Qwen3.8-27B in an M5 Max — Lianhuiq · 2026-09-19
• Inco Splash hits 144 tok/s running Qwen3.8-27B on an M5 Max, 3x faster than Ollama — TheMoonMidas · 2026-09-19