← Back to community benchmarks

Qwen3.6-35B-A3B

M2 Max (38c) · 96 GB · 8bit · 2026-05-05

Performance

8k

tokens

630.1

PP tok/s

61.8

TG tok/s

13001

TTFT (ms)

36.5

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 96 GB

GPU Cores 38

Software

oMLX v0.3.8

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	638.4	67.4	35.4 GB	view
4k	693.7	64.1	36.2 GB	view
8k	630.1	61.8	36.5 GB	current
16k	586.0	55.4	37.4 GB	view
32k	520.2	45.9	38.5 GB	view
64k	423.4	34.3	41.9 GB	view