← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 64 GB · 4bit · 2026-04-14

Performance

16k

tokens

3,498

PP tok/s

46.1

TG tok/s

4684

TTFT (ms)

41.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.5

macOS macOS 26.4.1

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,455	370.2	39.5 GB	view
4k	1,079	85.2	39.8 GB	view
8k	1,683	80.7	40.0 GB	view
16k	3,498	46.1	41.3 GB	current
32k	3,179	45.0	41.9 GB	view
64k	2,447	43.9	43.8 GB	view
128k	1,784	41.4	46.5 GB	view