← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M5 Max (40c) · 64 GB · 4bit · 2026-04-19

Performance

4k

tokens

3,794

PP tok/s

112.9

TG tok/s

1080

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M5 Max (40c)

Memory 64 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	2,195	117.9	20.2 GB	view
4k	3,794	112.9	21.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	117.9	1.00×
2×	193.2	1.64×
4×	286.5	2.43×