← Back to community benchmarks

Qwen3.5-122B-A10B-VisionMixed

M5 Max (40c) · 128 GB · 4bit · 2026-04-04

Performance

8k

tokens

1,521

PP tok/s

34.9

TG tok/s

5387

TTFT (ms)

75.3

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.2

macOS macOS 26.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	992.9	36.6	73.3 GB	view
4k	1,470	35.9	74.7 GB	view
8k	1,521	34.9	75.3 GB	current