← Back to community benchmarks

Qwen3.5-122B-A10B

M3 Max (40c) · 128 GB · 4bit · 2026-04-23

Performance

16k

tokens

1,490

PP tok/s

42.8

TG tok/s

10995

TTFT (ms)

69.4

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.7rc2

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	433.9	45.5	66.0 GB	view
16k	1,490	42.8	69.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	45.5	1.00×
2×	61.2	1.35×