← Back to community benchmarks

Qwopus3.6-27B-v2-oQ4-fp16-mtp

M3 Ultra (60c) · 96 GB · 4bit · 2026-06-03

Performance

4k

tokens

344.4

PP tok/s

42.4

TG tok/s

11892

TTFT (ms)

18.2

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.4.0rc2

macOS macOS 26.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	325.3	44.0	16.7 GB	view
4k	344.4	42.4	18.2 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	44.0	1.00×
2×	86.0	1.95×
4×	168.7	3.83×