← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 48 GB · 4bit · 2026-04-20

Performance

4k

tokens

1,681

PP tok/s

107.7

TG tok/s

2437

TTFT (ms)

20.0

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 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,320	108.8	19.2 GB	view
4k	1,681	107.7	20.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	108.8	1.00×
2×	186.7	1.72×
4×	271.2	2.49×