← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Ultra (60c) · 128 GB · 4bit · 2026-03-10

Performance

4k

tokens

1,141

PP tok/s

77.2

TG tok/s

3591

TTFT (ms)

20.2

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 128 GB

GPU Cores 60

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,049	79.3	20.0 GB	view
4k	1,141	77.2	20.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	79.3	1.00×
2×	134.7	1.70×