← Back to community benchmarks

Qwen3-Coder-Next

M1 Max (24c) · 64 GB · 3bit · 2026-03-12

Performance

4k

tokens

320.1

PP tok/s

39.1

TG tok/s

12795

TTFT (ms)

33.9

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 64 GB

GPU Cores 24

Software

oMLX v0.2.9

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	278.0	41.2	33.8 GB	view
4k	320.1	39.1	33.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	41.2	1.00×
2×	55.9	1.36×
4×	68.3	1.66×