← Back to community benchmarks

Qwen3.5-35B-A3B

M4 Max (40c) · 128 GB · 4bit · 2026-04-15

Performance

4k

tokens

1,714

PP tok/s

114.2

TG tok/s

2390

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.3.5.dev1

macOS macOS 15.6

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,253	120.2	19.3 GB	view
4k	1,714	114.2	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	120.2	1.00×
2×	194.7	1.62×
4×	267.1	2.22×