← Back to community benchmarks

Qwen3.5-35B-A3B

M1 Pro (16c) · 32 GB · 4bit · 2026-03-10

Performance

1k

tokens

274.6

PP tok/s

47.6

TG tok/s

3729

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M1 Pro (16c)

Memory 32 GB

GPU Cores 16

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	47.6	1.00×
4×	56.7	1.19×