← Back to community benchmarks

Qwen3.6-35B-A3B

M2 Ultra (60c) · 64 GB · 4bit · 2026-05-01

Performance

32k

tokens

1,027

PP tok/s

65.0

TG tok/s

31895

TTFT (ms)

22.4

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 64 GB

GPU Cores 60

Software

oMLX v0.3.8

macOS macOS 26.3.1

Context 32,768

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	904.5	84.7	19.3 GB	view
32k	1,027	65.0	22.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	84.7	1.00×
2×	139.7	1.65×