← Back to community benchmarks

Qwen3.6-35B-A3B

M2 Max (30c) · 64 GB · 8bit · 2026-05-15

Performance

16k

tokens

589.0

PP tok/s

54.1

TG tok/s

27816

TTFT (ms)

37.4

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 64 GB

GPU Cores 30

Software

oMLX v0.3.8

macOS macOS 26.5

Context 16,384

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	520.4	64.7	35.4 GB	view
4k	615.3	61.9	36.2 GB	view
8k	612.1	59.1	36.5 GB	view
16k	589.0	54.1	37.4 GB	current
32k	533.2	47.3	38.9 GB	view
64k	447.4	37.0	41.9 GB	view
128k	324.6	26.0	47.9 GB	view