← Back to community benchmarks

Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 4bit · 2026-05-19

Performance

1k

tokens

1,032

PP tok/s

88.6

TG tok/s

993

TTFT (ms)

43.1

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.9rc1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,032	88.6	43.1 GB	current
4k	1,339	85.9	44.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	88.6	1.00×
2×	140.1	1.58×
4×	194.9	2.20×