← Back to community benchmarks

Qwen3.5-27BMTP

M1 Max (24c) · 32 GB · 4bit · 2026-05-21

Performance

4k

tokens

67.7

PP tok/s

11.9

TG tok/s

60475

TTFT (ms)

17.6

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.3.9rc1

macOS macOS 26.5

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	66.9	12.6	16.1 GB	view
4k	67.7	11.9	17.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.6	1.00×
2×	25.0	1.98×
4×	59.3	4.71×