← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (40c) · 64 GB · 4bit · 2026-07-24

Performance

128k

tokens

557.0

PP tok/s

41.8

TG tok/s

235311

TTFT (ms)

32.1

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.5.1

macOS macOS 26.5.2

Context 131,072

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
64k	885.7	59.6	25.0 GB	view
128k	557.0	41.8	32.1 GB	current
195k	189.4	33.9	38.5 GB	view