← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 8bit · 2026-03-16

Performance

4k

tokens

1,238

PP tok/s

64.1

TG tok/s

3309

TTFT (ms)

80.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.8

macOS macOS 26.3.1

Context 4,096