← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

M3 Max (40c) · 128 GB · 5bit · 2026-04-04

Performance

16k

tokens

1,451

PP tok/s

11.6

TG tok/s

11290

TTFT (ms)

84.1

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.2

macOS macOS 26.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	427.6	41.5	80.5 GB	view
4k	484.8	39.4	82.0 GB	view
8k	477.6	37.1	82.6 GB	view
16k	1,451	11.6	84.1 GB	current