← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-22

Performance

4k

tokens

1,613

PP tok/s

60.5

TG tok/s

2539

TTFT (ms)

67.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.19

macOS macOS 26.3.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,263	63.1	66.4 GB	view
4k	1,613	60.5	67.9 GB	current
195k	404.3	14.7	96.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	63.1	1.00×
2×	102.1	1.62×
4×	125.5	1.99×