← Back to community benchmarks

Qwen3.5-35B-A3B

M2 Ultra (76c) · 192 GB · 4bit · 2026-03-19

Performance

4k

tokens

1,486

PP tok/s

76.5

TG tok/s

2757

TTFT (ms)

21.0

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 192 GB

GPU Cores 76

Software

oMLX v0.2.18

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,261	80.2	20.1 GB	view
4k	1,486	76.5	21.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	80.2	1.00×
2×	136.4	1.70×
4×	208.3	2.60×