MLX over Vulkan hits 124 tok/s on RTX 5060 Ti, beating llama.cpp CUDA by 25%

SumitGup · x · 2026-11-22

Joshua Warren shipped an Omarchy-mlx update where Apple's MLX framework, running over Vulkan on Linux, decodes Qwen3-4B 4-bit at 124 tok/s on an RTX 5060 Ti eGPU — beating llama.cpp CUDA's 101 tok/s on the same card, challenging the idea that CUDA is NVIDIA's moat.

Key technical detail:

Takeaway: framework-level scheduling optimization still has big headroom, and MLX-Linux-Vulkan now outruns CUDA on NVIDIA's own silicon.

Original post →

More from Infra

Infra channel →