← Back to community benchmarks

Qwen3.5-27B7bit

M4 Pro (20c) · 64 GB · 6bit · 2026-03-10

Performance

4k

tokens

117.1

PP tok/s

10.2

TG tok/s

34972

TTFT (ms)

23.9

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 64 GB

GPU Cores 20

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	119.7	10.4	23.6 GB	view
4k	117.1	10.2	23.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	10.4	1.00×
2×	17.5	1.68×
4×	18.9	1.82×