← Back to community benchmarks

Qwen3.5-122B-A10Boptimized

M2 Max (38c) · 96 GB · 3bit · 2026-04-05

Performance

1k

tokens

198.9

PP tok/s

34.6

TG tok/s

5149

TTFT (ms)

54.3

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.4

macOS macOS 15.7.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	198.9	34.6	54.3 GB	current
4k	226.0	32.6	55.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	34.6	1.00×
2×	47.5	1.37×
4×	94.9	2.74×