← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Ultra (60c) · 192 GB · 4bit · 2026-03-23

Performance

4k

tokens

1,185

PP tok/s

75.4

TG tok/s

3458

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M2 Ultra (60c)

Memory 192 GB

GPU Cores 60

Software

oMLX v0.2.19

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,107	77.8	20.1 GB	view
4k	1,185	75.4	21.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	77.8	1.00×
2×	127.4	1.64×
4×	193.8	2.49×