← Back to community benchmarks

Qwen3.6-35B-A3B

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

Performance

1k

tokens

622.1

PP tok/s

44.8

TG tok/s

1646

TTFT (ms)

35.4

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 1,024

Performance by Context Length

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