← Back to community benchmarks

Qwen3-Coder-Next

M5 Max (40c) · 128 GB · 8bit · 2026-07-17

Performance

64k

tokens

1,894

PP tok/s

59.1

TG tok/s

34602

TTFT (ms)

86.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 65,536