← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-04-26

Performance

1k

tokens

2,300

PP tok/s

186.6

TG tok/s

445

TTFT (ms)

67.0

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	2,300	186.6	67.0 GB	current
4k	2,701	170.7	68.0 GB	view
8k	2,153	171.8	68.2 GB	view
16k	1,466	155.4	68.9 GB	view