← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 48 GB · 4bit · 2026-04-19

Performance

1k

tokens

1,447

PP tok/s

383.3

TG tok/s

708

TTFT (ms)

20.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.3.6

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,447	383.3	20.6 GB	current
4k	624.9	112.9	20.0 GB	view
8k	1,715	104.1	20.4 GB	view