← Back to community benchmarks

Qwen3.5-35B-A3B

M5 Pro (20c) · 64 GB · 4bit · 2026-03-19

Performance

1k

tokens

1,954

PP tok/s

95.5

TG tok/s

524

TTFT (ms)

20.1

Peak mem (GB)

Hardware

Chip M5 Pro (20c)

Memory 64 GB

GPU Cores 20

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	1,954	95.5	20.1 GB	current
4k	2,291	94.6	21.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	95.5	1.00×
2×	149.9	1.57×
4×	196.3	2.06×