← Back to community benchmarks

Qwen3.5-122B-A10B-5bit

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

Performance

1k

tokens

427.6

PP tok/s

41.5

TG tok/s

2395

TTFT (ms)

80.5

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.2

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	427.6	41.5	80.5 GB	current
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	view