← Back to community benchmarks

Qwen3.5-27B

M4 Max (40c) · 48 GB · 4bit · 2026-03-12

Performance

1k

tokens

247.2

PP tok/s

28.7

TG tok/s

4143

TTFT (ms)

16.6

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.2.8

macOS macOS 15.6.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	247.2	28.7	16.6 GB	current
4k	243.4	27.4	17.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.7	1.00×
2×	53.9	1.88×
4×	58.3	2.03×