← Back to community benchmarks

RepublicOfKorokke-Qwen3-Coder-Next

M4 Max (40c) · 128 GB · 4bit · 2026-04-06

Performance

4k

tokens

1,262

PP tok/s

78.0

TG tok/s

3246

TTFT (ms)

41.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.4

macOS macOS 15.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,039	81.5	40.8 GB	view
4k	1,262	78.0	41.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	81.5	1.00×
2×	131.0	1.61×
4×	178.5	2.19×