← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Max (40c) · 128 GB · 4bit · 2026-04-16

Performance

4k

tokens

3,877

PP tok/s

129.4

TG tok/s

1057

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,384	134.0	19.3 GB	view
4k	3,877	129.4	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	134.0	1.00×
2×	222.2	1.66×
4×	327.0	2.44×
8×	432.3	3.23×