← Back to community benchmarks

Qwen3.5-27B

M4 Max (40c) · 128 GB · 4bit · 2026-03-10

Performance

8k

tokens

223.3

PP tok/s

26.5

TG tok/s

36686

TTFT (ms)

17.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.6

macOS macOS 15.7.4

Context 8,192

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	248.4	28.7	16.6 GB	view
4k	248.0	27.8	17.0 GB	view
8k	223.3	26.5	17.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	28.7	1.00×
2×	53.3	1.86×
4×	57.1	1.99×