← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-03-29

Performance

4k

tokens

1,413

PP tok/s

62.2

TG tok/s

2899

TTFT (ms)

67.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.0rc1

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,040	66.2	65.6 GB	view
4k	1,413	62.2	67.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	66.2	1.00×
2×	101.2	1.53×
4×	131.5	1.99×