← Back to community benchmarks

Qwen3.5-27B

M4 Pro (16c) · 48 GB · 4bit · 2026-03-10

Performance

1k

tokens

101.9

PP tok/s

15.2

TG tok/s

10048

TTFT (ms)

16.6

Peak mem (GB)

Hardware

Chip M4 Pro (16c)

Memory 48 GB

GPU Cores 16

Software

oMLX v0.2.6

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	101.9	15.2	16.6 GB	current
4k	101.0	14.3	17.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	15.2	1.00×
2×	24.2	1.59×
4×	24.9	1.64×