← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Max (38c) · 64 GB · 8bit · 2026-04-16

Performance

32k

tokens

658.7

PP tok/s

43.0

TG tok/s

49747

TTFT (ms)

38.5

Peak mem (GB)

Hardware

Chip M2 Max (38c)

Memory 64 GB

GPU Cores 38

Software

oMLX v0.3.5

macOS macOS 15.7.5

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	625.9	65.5	35.4 GB	view
4k	756.9	61.7	36.2 GB	view
8k	757.4	58.4	36.5 GB	view
16k	727.1	52.4	37.1 GB	view
32k	658.7	43.0	38.5 GB	current
64k	545.8	31.4	41.2 GB	view
128k	375.0	17.2	46.5 GB	view