← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 8bit · 2026-03-12

Performance

4k

tokens

1,669

PP tok/s

77.3

TG tok/s

2455

TTFT (ms)

36.3

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.9

macOS macOS 26.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,463	81.1	36.2 GB	view
4k	1,669	77.3	36.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	81.1	1.00×
2×	131.8	1.63×
4×	190.6	2.35×