← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 4bit · 2026-04-15

Performance

16k

tokens

1,241

PP tok/s

71.0

TG tok/s

13203

TTFT (ms)

87.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,239	83.9	86.6 GB	view
8k	1,321	79.9	86.9 GB	view
16k	1,241	71.0	87.6 GB	current
32k	1,077	58.3	89.0 GB	view
64k	840.6	42.1	91.8 GB	view