← Back to community benchmarks

Qwen3.5-122B-A10B-oQ2

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

Performance

4k

tokens

543.0

PP tok/s

46.3

TG tok/s

7543

TTFT (ms)

42.6

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 4,096

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	current
16k	451.8	41.4	44.4 GB	view