← Back to community benchmarks

Qwen3.5-122B-A10B-Text-qx64-hi

M3 Max (40c) · 128 GB · 6bit · 2026-05-05

Performance

1k

tokens

432.5

PP tok/s

39.5

TG tok/s

2368

TTFT (ms)

86.6

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	432.5	39.5	86.6 GB	current
4k	497.1	38.2	87.9 GB	view
8k	487.2	35.6	88.7 GB	view
16k	423.3	35.0	90.0 GB	view