← Back to community benchmarks

Qwen3.5-27B

M2 (10c) · 24 GB · 4bit · 2026-03-10

Performance

4k

tokens

31.1

PP tok/s

5.6

TG tok/s

131859

TTFT (ms)

16.9

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	31.0	5.8	16.6 GB	view
4k	31.1	5.6	16.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	5.8	1.00×
2×	8.2	1.41×
4×	8.4	1.45×