← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-04-26

Performance

1k

tokens

2,953

PP tok/s

264.7

TG tok/s

347

TTFT (ms)

36.1

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,953	264.7	36.1 GB	current
4k	1,006	96.5	37.6 GB	view
8k	3,910	93.9	37.9 GB	view
64k	4,797	45.0	40.7 GB	view
128k	3,365	39.4	42.7 GB	view