← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 64 GB · 4bit · 2026-03-13

Performance

4k

tokens

1,264

PP tok/s

82.9

TG tok/s

3241

TTFT (ms)

43.2

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.2.9

macOS macOS 15.6.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,084	87.2	43.0 GB	view
4k	1,264	82.9	43.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	87.2	1.00×
2×	143.2	1.64×
4×	201.1	2.31×