← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M3 Max (40c) · 128 GB · 5bit · 2026-04-04

Performance

32k

tokens

1,073

PP tok/s

11.3

TG tok/s

30554

TTFT (ms)

86.7

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.2

macOS macOS 26.4

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
16k	1,223	11.6	85.2 GB	view
32k	1,073	11.3	86.7 GB	current
64k	973.1	11.0	88.5 GB	view