← Back to community benchmarks

Qwen3.5-27B

M2 Ultra (76c) · 192 GB · 4bit · 2026-03-10

Performance

4k

tokens

228.5

PP tok/s

31.4

TG tok/s

17926

TTFT (ms)

17.0

Peak mem (GB)

Hardware

Chip M2 Ultra (76c)

Memory 192 GB

GPU Cores 76

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	226.3	33.5	16.6 GB	view
4k	228.5	31.4	17.0 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.5	1.00×
2×	47.1	1.41×
4×	54.4	1.62×