← Back to community benchmarks

Qwen3.6-35B-A3B

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

Performance

8k

tokens

1,715

PP tok/s

104.1

TG tok/s

4778

TTFT (ms)

20.4

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 8,192

Performance by Context Length

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