← Back to community benchmarks

Qwen3.5-35B-A3B

M3 Max (40c) · 48 GB · 4bit · 2026-03-16

Performance

1k

tokens

1,262

PP tok/s

93.0

TG tok/s

812

TTFT (ms)

20.0

Peak mem (GB)

Hardware

Chip M3 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.2.13

macOS macOS 26.2

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	93.0	1.00×
2×	146.8	1.58×
4×	220.2	2.37×