← Back to community benchmarks

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

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

Performance

8k

tokens

487.2

PP tok/s

35.6

TG tok/s

16814

TTFT (ms)

88.7

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 8,192

Performance by Context Length

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