← Back to community benchmarks

Qwen3-Coder-Next

M3 Max (40c) · 64 GB · 4bit · 2026-05-05

Performance

1k

tokens

962.8

PP tok/s

64.0

TG tok/s

1064

TTFT (ms)

43.1

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	962.8	64.0	43.1 GB	current
4k	1,135	64.7	44.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	64.0	1.00×
2×	107.2	1.68×
4×	159.3	2.49×