← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M5 Max (40c) · 128 GB · 5bit · 2026-04-01

Performance

64k

tokens

767.8

PP tok/s

29.3

TG tok/s

85357

TTFT (ms)

90.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.0

macOS macOS 26.4

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	987.9	55.6	79.8 GB	view
4k	1,364	55.7	81.1 GB	view
16k	1,155	46.0	82.9 GB	view
64k	767.8	29.3	90.2 GB	current