← Back to community benchmarks

Qwen3.5-122B-A10B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-03-27

Performance

8k

tokens

1,469

PP tok/s

54.1

TG tok/s

5577

TTFT (ms)

69.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.23

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,032	58.3	67.0 GB	view
4k	1,451	55.9	68.4 GB	view
8k	1,469	54.1	69.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	58.3	1.00×
2×	94.0	1.61×
4×	113.7	1.95×