MLX Community Challenge Boosts Qwen 3.8 Speed on Apple Silicon by Over 150%

A community MLX optimization challenge for the Qwen 3.8 27B model delivered a 151%+ decoding speedup on Apple Silicon Macs, demonstrating the platform's potential for running dense large models.

2026-08-16 ~ 2026-08-16 · 2 related posts

• Qwen 3.8 runs 151% faster on Apple Silicon via community challenge — gajesh · 2026-08-16
• Challenge boosts Qwen 3.8 speed by 152% on Mac — gajesh · 2026-08-16