← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-30

Performance

1k

tokens

1,017

PP tok/s

66.4

TG tok/s

1007

TTFT (ms)

65.6

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.0rc1

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,017	66.4	65.6 GB	current
4k	1,472	63.1	67.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	66.4	1.00×
2×	100.0	1.51×
4×	135.3	2.04×