← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Max (38c) · 64 GB · 4bit · 2026-04-17

Performance

8k

tokens

740.6

PP tok/s

70.6

TG tok/s

11062

TTFT (ms)

20.4

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 64 GB

GPU Cores 38

Software

oMLX v0.3.6

macOS macOS 15.7.5

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	604.5	82.2	19.3 GB	view
4k	730.9	77.5	20.0 GB	view
8k	740.6	70.6	20.4 GB	current
16k	713.1	62.8	21.0 GB	view