← Back to community benchmarks

Qwopus3.6-27B-v2-oQ5-fp16-mtp

M2 Max (30c) · 32 GB · 5bit · 2026-06-19

Performance

4k

tokens

151.9

PP tok/s

17.5

TG tok/s

26960

TTFT (ms)

20.9

Peak mem (GB)

Hardware

Chip M2 Max (30c)

Memory 32 GB

GPU Cores 30

Software

oMLX v0.4.4

macOS macOS 26.5.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	147.5	18.0	19.5 GB	view
4k	151.9	17.5	20.9 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	18.0	1.00×
2×	23.3	1.29×
4×	47.0	2.61×