← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 64 GB · 8bit · 2026-04-28

Performance

8k

tokens

840.5

PP tok/s

42.9

TG tok/s

9746

TTFT (ms)

36.5

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.8rc1

macOS macOS 26.4.1

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	622.1	44.8	35.4 GB	view
4k	826.6	46.1	36.2 GB	view
8k	840.5	42.9	36.5 GB	current
16k	768.9	37.2	37.1 GB	view