← Back to community benchmarks

Qwen3.5-122B-A10B-oQ2

M4 Max (40c) · 64 GB · 2bit · 2026-04-16

Performance

16k

tokens

451.8

PP tok/s

41.4

TG tok/s

36267

TTFT (ms)

44.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	515.3	47.3	41.3 GB	view
4k	543.0	46.3	42.6 GB	view
16k	451.8	41.4	44.4 GB	current