← Back to community benchmarks

Qwen3.5-122B-A10B

M2 Ultra (60c) · 192 GB · 4bit · 2026-03-20

Performance

1k

tokens

351.9

PP tok/s

44.4

TG tok/s

2910

TTFT (ms)

66.4

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 192 GB

GPU Cores 60

Software

oMLX v0.2.19

macOS macOS 15.6

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	351.9	44.4	66.4 GB	current
4k	386.1	39.3	67.9 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	44.4	1.00×
2×	66.2	1.49×
4×	86.8	1.95×