← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-03-12

Performance

16k

tokens

1,330

PP tok/s

64.0

TG tok/s

12316

TTFT (ms)

37.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.9

macOS macOS 26.2

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
8k	1,669	73.8	36.5 GB	view
16k	1,330	64.0	37.0 GB	current
32k	1,054	42.9	37.8 GB	view
64k	656.4	16.7	39.5 GB	view