← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 64 GB · 8bit · 2026-05-19

Performance

4k

tokens

3,685

PP tok/s

97.1

TG tok/s

1112

TTFT (ms)

36.2

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 GB

GPU Cores 40

Software

oMLX v0.3.9.dev1

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,982	98.3	35.4 GB	view
4k	3,685	97.1	36.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	98.3	1.00×
2×	160.6	1.63×
4×	237.7	2.42×