← Back to community benchmarks

Qwen3.5-35B-A3B

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

Performance

1k

tokens

1,107

PP tok/s

77.8

TG tok/s

925

TTFT (ms)

20.1

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 1,024

Performance by Context Length

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

Batching Results

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