← Back to community benchmarks

Qwen3.5-122B-A10B

M5 Max (40c) · 128 GB · 4bit · 2026-04-04

Performance

64k

tokens

850.9

PP tok/s

33.6

TG tok/s

77021

TTFT (ms)

76.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.2

macOS macOS 26.3.2

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
4k	1,434	62.1	67.0 GB	view
8k	1,523	56.9	67.7 GB	view
16k	1,443	52.7	68.9 GB	view
32k	1,120	37.4	71.2 GB	view
64k	850.9	33.6	76.1 GB	current
128k	546.3	21.4	85.7 GB	view