← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M4 Max (40c) · 128 GB · 5bit · 2026-04-04

Performance

8k

tokens

551.0

PP tok/s

45.6

TG tok/s

14868

TTFT (ms)

81.9

Peak mem (GB)

Hardware

Chip M4 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	491.4	50.6	79.8 GB	view
4k	557.0	48.4	81.3 GB	view
8k	551.0	45.6	81.9 GB	current
16k	521.4	40.5	83.1 GB	view
32k	461.7	33.9	85.5 GB	view