← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · 8bit · 2026-05-14

Performance

64k

tokens

2,295

PP tok/s

70.5

TG tok/s

28551

TTFT (ms)

41.9

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 65,536

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	2,219	101.7	35.4 GB	view
4k	3,724	95.5	36.2 GB	view
8k	3,914	97.5	36.5 GB	view
16k	3,829	91.0	37.4 GB	view
32k	3,262	85.1	38.9 GB	view
64k	2,295	70.5	41.9 GB	current
128k	1,226	46.5	47.9 GB	view