← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Max (40c) · 48 GB · 4bit · 2026-03-14

Performance

4k

tokens

3,137

PP tok/s

119.5

TG tok/s

1306

TTFT (ms)

20.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.2.11

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,434	125.2	20.0 GB	view
4k	3,137	119.5	20.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	125.2	1.00×
2×	215.5	1.72×
4×	336.3	2.69×