← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Max (30c) · 64 GB · 6bit · 2026-03-13

Performance

16k

tokens

477.3

PP tok/s

44.1

TG tok/s

34329

TTFT (ms)

28.9

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.2.10

macOS macOS 15.7.4

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	553.5	61.1	28.1 GB	view
4k	558.6	58.3	28.3 GB	view
8k	503.1	53.3	28.5 GB	view
16k	477.3	44.1	28.9 GB	current
32k	427.7	35.2	29.7 GB	view
64k	364.1	25.9	31.4 GB	view