← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Max (30c) · 96 GB · 4bit · 2026-03-30

Performance

16k

tokens

317.0

PP tok/s

27.9

TG tok/s

51682

TTFT (ms)

68.9

Peak mem (GB)

Hardware

Chip M3 Max (30c)

Memory 96 GB

GPU Cores 30

Software

oMLX v0.3.0rc1

macOS macOS 26.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	323.5	34.6	65.6 GB	view
4k	362.3	33.1	67.0 GB	view
8k	330.2	31.0	67.7 GB	view
16k	317.0	27.9	68.9 GB	current
32k	294.6	23.2	71.2 GB	view
64k	220.3	13.8	76.1 GB	view