← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-04-12

Performance

32k

tokens

1,391

PP tok/s

66.9

TG tok/s

23562

TTFT (ms)

38.5

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.4

macOS macOS 26.4.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,369	89.6	35.4 GB	view
4k	1,704	85.6	36.2 GB	view
8k	1,709	82.9	36.5 GB	view
16k	1,604	75.4	37.1 GB	view
32k	1,391	66.9	38.5 GB	current
64k	1,075	47.1	41.2 GB	view